跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+979新增论文
+781其中 AI 相关
+119已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 19:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-20 09:13 — 2026-11-21 09:13(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 08:48最近发现新增版本:2026-11-20 19:58库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

28,961 已收录论文24,030 AI 相关8,912 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 5,296 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
新论文 · v1arXiv:2611.26613

AgentRoboCritic:理解前沿智能体在直接机器人控制中的能力

AgentRoboCritic: Understanding the Capability of Frontier Agents on Direct Robot Control

Yiyang Du, Yuxuan Kuang, Qitao Zhao, Yixuan Wang, Zhanqiu Guo, Yi Xu, Xin Li, Wenbin He 等 10 位作者

AI 速读 基于摘要

作者提出以意图为依据的动作级批评框架 AgentRoboCritic,在12个操作基准上系统分析前沿多模态语言智能体直接输出底层动作控制机器人的能力与失败模式。

cs.RO · cs.CL · cs.CV

查看原文摘要

Frontier multimodal language agents such as GPT-6 Astra have demonstrated strong capabilities in controlling robots directly via low-level numerical actions without high-level primitives. However, existing benchmarks report only episode-level success rates, which show neither how these agents succeed nor where they fail. In this paper, we present a systematic action-level analysis of frontier agents on direct robot control across 12 manipulation benchmarks. We introduce AgentRoboCritic, an intent-grounded critique framework in which the policy agent states a local intent alongside each action, and a critic evaluates the action's outcome and failure mode against this intent. Our action-level analysis demonstrates the promising capabilities of frontier agents on direct robot control, including closed-loop recovery from local execution failures, reliable semantic grounding across diverse scenes, and strong zero-shot manipulation without task-specific adaptation. It also identifies their current limitations, including task-relevant physical execution bottlenecks such as grasping and alignment, and uneven recovery across failure modes. Finally, we validate our critic on a 400-action human-annotated benchmark and release a dataset of 12,844 annotated actions alongside a fine-tuned open-source critic, Muse-Glimmer-30B, whose failure-mode accuracy rises from 32.58% to 74.24%, enabling low-cost action-level analysis.

版本更新 · v2arXiv:2610.01054

用任务算子刻画上下文学习动态

Capturing In-Context Learning Dynamics with Task Operators

Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Wenqian Ye, Aidong Zhang

AI 速读 基于摘要

作者提出任务算子(Task Operator),把上下文学习(ICL)中注意力头的仿射变换参数提取为对注意力输出投影的解析更新,从而在无需完整示例上下文的情况下近似 ICL 效果。

cs.CL · cs.AI · cs.LG

查看原文摘要

In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requires processing the full set of examples, resulting in inefficient deployments, and how ICL works mechanistically is not fully understood. Prior work compresses ICL into fixed activation vectors extracted from specific layers or positions, but these input-independent interventions fail on complex tasks where the output depends on fine-grained interactions with the input. By analyzing the ICL forward pass, we show that each attention head's output is an affine transformation of its context-masked counterpart, and that the parameters of this transformation are empirically stable across samples for a given task. Building on this, we introduce Task Operator (TO), which replays this transformation as an analytically derived update to the attention output projection. Across lexical, algorithmic, and reasoning tasks, TO achieves the best overall performance among prior methods and substantially narrows the gap between zero-shot inference and ICL. We further show that the extracted knowledge concentrates in a task-specific sparse circuit across layers and positions, and that averaging operators from disjoint demonstration batches enables effective many-shot scaling without expanding the context window. Our code is available at https://github.com/gzxiong/task_operator.

版本更新 · v2arXiv:2605.20158

重新审视大型视觉语言模型在胸部X射线推理中的视觉归因

Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models

Guangzhi Xiong, Qiao Jin, Sanchit Sinha, Zhiyong Lu, Aidong Zhang

AI 速读 基于摘要

作者通过因果评估框架发现现有视觉归因方法常无法识别LVLM在胸片推理中使用的证据,并提出基于概念的MedFocus方法以改善归因。

cs.CV · cs.AI · cs.CL

查看原文摘要

Large Vision Language Models (LVLMs) show promise in medical applications, but their inability to faithfully ground responses in visual evidence raises serious concerns about clinical trustworthiness. While visual attribution methods are widely used to explain LVLM predictions, whether these explanations actually reflect the visual evidence underlying the model's decision is largely unverified, since ground-truth annotations for internal model reasoning are typically unavailable. We address this question for chest X-ray (CXR) reasoning by developing a causal evaluation framework that retains only CXR-VQA samples for which the expert-annotated region is verified, via counterfactual editing, to be causally responsible for the model's prediction. Using this framework across 11 attribution methods, six open-source LVLMs, and two output modes (direct answer and step-by-step reasoning), we find that existing attribution methods often fail to identify the evidence used by LVLMs. To address this failure, we propose MedFocus, a concept-based attribution method that localizes clinically meaningful anatomical regions via unbalanced optimal transport and measures their causal effect on model outputs through targeted interventions. MedFocus produces spatial, concept-level, and token-level attributions and substantially outperforms prior methods, taking a step toward more trustworthy attribution for medical LVLMs. Our data and code are available at https://github.com/gzxiong/medfocus/.

版本更新 · v2arXiv:2605.06342

别失去焦点:通过键正交投影的激活引导

Don't Lose Focus: Activation Steering via Key-Orthogonal Projections

Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik

AI 速读 基于摘要

作者提出SKOP方法,通过键正交投影约束激活引导对注意力匹配的干扰,在保持引导效果的同时大幅减少推理与检索性能退化。

cs.CL

查看原文摘要

Activation steering controls LLM behaviour towards target behaviour by intervening in internal representations, yet it often degrades reasoning and retrieval performance. We argue that a primary cause of this trade-off is attention rerouting: steering vectors alter query-key matching, shifting attention away from contextually important tokens toward less informative ones. To address this, we propose Steering via Key-Orthogonal Projections (SKOP), a steering method that constrains harmful attention rerouting without eliminating steering efficacy. SKOP achieves this by preserving attention patterns on a small set of focus tokens the model relies on for reasoning and retrieval, while allowing redistribution among less critical tail tokens. Across multiple steering benchmarks, we show that SKOP achieves the best joint steering-utility trade-off, reducing utility degradation by 5-7x while retaining over 95% of vanilla steering efficacy. Our results further suggest that, in long-context retrieval settings where vanilla steering approaches are ineffective, SKOP can maintain robust performance by avoiding attention rerouting.

新论文 · v1arXiv:2611.26584

被表征但被误读:后训练改变语言模型读取其表征的方式

Represented but misread: Post-training changes how language models read out what they represent

Jochen Laubrock

AI 速读 基于摘要

后训练主要改变语言模型如何从内部表征中读出答案,而非改变表征本身,且这种读出方向可被少量训练信号设定。

cs.CL · cs.LG

查看原文摘要

Does post-training change what a language model represents, or how this representation is read out into an answer? We compared linear probes with the models' own answers, analyzed with signal detection theory, in six open-weight base models and their post-trained versions. For judgments of whether German texts were written by a human or an AI, probes and word n-gram classifiers separated the classes well, but the answers did not and often ordered the texts inversely. Post-training lowered the sensitivity of the answers on average ($Δd' = -0.34$ across model families; -0.29 across three prompts). It also changed the use of a stated base rate: Base models shifted their log-odds by less than the stated change in prior odds, most post-trained models by more. In two models with stage-wise checkpoints, the change occurred during supervised fine-tuning, model stitching implicated the early layers, and from mid-depth on internal states at positions after the text, not those of the text, transferred the change between checkpoints. Our corpora cannot be shared, so we add a case reproducible from public data, the truth of negated statements. Here, post-training acted in the opposite direction: Probes decoded truth at or near ceiling in every model, the answers of several base models did not use it, and post-training repaired them; by mid-depth the repair resided at the positions after the statement; below it, the representation of the statement contributed, strongly in one of four models. In a training study, adding 2,000 correctly labeled authorship judgments of news texts to otherwise identical fine-tuning data improved the answers on our newspaper and textbook corpora and inverted them on the chats, where they followed a news-trained probe of the base model. Post-training thus changed how a judgment is read out of what a model represents, and a small training signal can set its direction.

版本更新 · v2arXiv:2607.15277

划分、提示、聚合:语言模型中的统计自洽性

Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models

Patrik Wolf, Thomas Kleine Buening, Andreas Krause, Celestine Mendler-Dünner

AI 速读 基于摘要

作者通过二叉树递归划分总体并提示LLM估计子群体条件分布,检验其聚合后是否满足全概率公式,发现广泛违反自洽性,并揭示“宏观谬误”现象。

cs.CL

查看原文摘要

Large language models (LLMs) are often used to perform a form of conditional inference. In-context learning is one implicit way to do this. The prompt specifies a context and the model's output is treated as an estimate of the corresponding conditional distribution. If this interpretation holds, then LLM estimates should satisfy basic probabilistic identities. In particular, the law of total probability asserts that prior-weighted conditional distributions aggregate into population-level marginals over any valid partition of the population. In this work, we investigate to what extent LLM estimates adhere to this self-consistency principle. We use binary trees as an evaluation scaffold to recursively partition a population into increasingly fine-grained subpopulations. We then prompt LLMs with verbalized subpopulation descriptions in context, aggregate the resulting estimates back into population-level estimates, and compare them across partitions of varying granularity. Translating these comparisons into a benchmark score and evaluating frontier models across problem domains, we demonstrate widespread violations of basic consistency properties. An in-depth study of persona prompting further reveals a pattern we call the macro fallacy: estimates reconstructed from more fine-grained subpopulation responses are often better aligned with human reference data than direct population-level estimates. The effect persists across variations in partitioning, verbalization, and estimation task, suggesting that models possess relevant subpopulation knowledge but do not reliably propagate it into aggregate estimates. This gap establishes statistical self-consistency as an unsaturated, reference-free criterion for evaluating LLMs.

版本更新 · v4arXiv:2605.03799

自然语言处理:从经典文本处理到多模态与智能体系统的应用研究实践

Natural Language Processing: An Applied Research Practicum From Classical Text Processing to Multimodal and Agentic Systems

Mullosharaf K. Arabov

AI 速读 基于摘要

这是一份以研究为导向的NLP实践指南,覆盖从分词、文本规范化到Transformer、大语言模型、检索增强生成、偏好对齐与多模态系统的完整流程,并特别关注低资源与形态丰富语言。

cs.CL

查看原文摘要

This preprint presents a systematic, research-oriented guide to modern natural language processing, covering the full NLP pipeline from tokenisation, text normalisation, vector representations, and classical machine learning to transformer architectures, large language models, retrieval-augmented generation, preference-based alignment, and multimodal systems. The material comprises eighteen practical works combining theoretical foundations, reproducible implementation examples, detailed experimental procedures, evaluation metrics, and research-oriented assignments. Each work includes three structured core tasks and optional advanced investigations. Common requirements for reporting, data provenance, experimental evaluation, and reproducibility are established across the guide. Particular attention is devoted to low-resource and morphologically rich languages, including Tajik, Tatar, and Bashkir. The guide addresses subword tokenisation, cross-lingual transfer, machine translation, language model adaptation, and the evaluation of NLP systems under limited data and computational resources. Advanced topics include prompt engineering, reasoning strategies, multi-agent collaboration, model compression, efficient inference, AI safety, and LLMOps. A capstone project integrates methods from different chapters into the development and evaluation of domain-specific NLP systems. The guide is intended for senior undergraduate students, graduate students, researchers, and developers interested in implementing and critically evaluating NLP methods.

版本更新 · v2arXiv:2611.24285

LipSpell:一种结合区别特征编辑距离、键盘几何与语料频率的语言无关拼写纠正音韵评分框架

LipSpell: A Language-Independent Phonetic Scoring Framework for Spelling Correction Combining Distinctive-Feature Edit Distance, Keyboard Geometry, and Corpus Frequency

Leonardo Araujo

AI 速读 基于摘要

LipSpell 提出一个语言无关的音韵评分引擎,结合 IPA 区别特征距离、键盘几何和语料频率,在多个英语基准和多语言场景中优于 Norvig、Hunspell 和 Aspell。

cs.CL

查看原文摘要

Automatic spelling correction must handle both keyboard typographical slips and cognitive or phonetic misspellings where writers approximate a word's pronunciation. Conventional spell checkers rely either on orthographic edit distance and keyboard proximity--which struggle when phonetic errors diverge by multiple characters--or on English-centric phonetic hashes such as Soundex and Metaphone. We present LipSpell, a unified, language-independent phonetic scoring engine paired with swappable language-specific G2P frontends, keyboard maps, and lexicons integrating: (1) a precomputed |P|x|P| phone-distance matrix from universal IPA distinctive features, (2) physical keyboard geometry, and (3) corpus unigram frequency priors, accelerated by a two-stage symmetric-delete and seven-class phonetic-code index. Across six English benchmarks (including 1,000 L2 errors from TOEFL-Spell), LipSpell outperforms Norvig and Hunspell on every dataset and beats Aspell on Norvig1 (78.52% vs. 75.56%), Holbrook (32.00% vs. 26.67%), and TOEFL-Spell (77.30% vs. 72.80%). Evaluated across six languages spanning five branches (Germanic, Romance, Slavic, Semitic, Turkic), three families (Indo-European, Afro-Asiatic, Turkic), and three scripts, LipSpell achieves strong fixed-weight transfer on Brazilian Portuguese (73.00% Top-1 on n=500 Wikipedia without NFD tolerance and 75.80% with NFD vs. 66.40% Norvig, 64.20% Hunspell, 64.00% Aspell) and Russian Cyrillic (85.67% vs. 78.50% Norvig). On 50/50 clean non-word splits with lexicon cleaning and weak-character indels, tuning yields strong gains over Norvig in Portuguese (86.97% vs. 76.75%), Turkish (81.67% vs. 79.05%), Hebrew Abjad (74.59% vs. 62.30%), and French (74.53% vs. 67.92%), while fixed weights remain optimal for English (80.37%) and Russian (85.67%).

版本更新 · v4arXiv:2605.29486

PhoneWorld:从真实应用轨迹到动态可验证的手机智能体环境

PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents

Yuxuan Liu, Xin Lai, Junyi Li, Pengyuan Lyu, Chenxin Li, Yiduo Guo, Zhengyao Fang, Yang Ding 等 24 位作者

AI 速读 基于摘要

PhoneWorld 将真实应用轨迹转化为可运行、可重置、可验证的 Android 环境,用于手机智能体的训练与评测。

cs.CL · cs.AI · cs.LG

查看原文摘要

Real applications provide the training setting closest to phone-agent deployment, but are difficult to reset, scale safely, and verify programmatically. Static screenshots and interaction trajectories preserve realistic evidence but cannot generate new experience. We introduce PhoneWorld, a trace-grounded framework that converts such evidence into runnable, resettable, and verifiable Android environments. PhoneWorld induces a usage-weighted interaction skeleton from observed pages, transitions, and state-changing operations; translates it into a behavior-grounded app specification; realizes the specification through an autonomous build--inspect--repair loop; and synthesizes executable tasks with programmatic verifiers. The resulting suite spans 34 consumer-facing apps across 16 domains and supports an audited online benchmark, verified trajectory generation, and online RL through common reset and verification interfaces. Evaluations with diverse general and open-source GUI agents show that PhoneWorld supports reliable end-to-end online interaction and exposes capabilities complementary to AndroidWorld. Controlled SFT experiments further show that PhoneWorld trajectories complement AndroidWorld supervision, transfer across online and offline benchmarks, and become more effective as data volume and app coverage increase. Under a matched RL budget, combining PhoneWorld mock-app rollouts with real-app rollouts improves performance over real-app RL alone on both real-phone tasks and AndroidWorld. Together, these results demonstrate that trace-grounded executable abstraction can bridge realistic mobile behavior and scalable agent learning, turning limited real-app evidence into a growing supply of controllable and verifiable environments for training and evaluation.

版本更新 · v3arXiv:2605.18565

MINTEval:评估长时程智能体系统在多目标干扰下的记忆能力

MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems

Hyunji Lee, Justin Chih-Yao Chen, Joykirat Singh, Zaid Khan, Elias Stengel-Eskin, Mohit Bansal

AI 速读 基于摘要

作者提出 MINTEval 基准,用于评测长时程、信息频繁更新且相互干扰的场景下,记忆增强智能体的召回与多证据聚合推理能力。

cs.CL · cs.AI

查看原文摘要

Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accurate recall and aggregated reasoning over multiple pieces of information. However, existing benchmarks focus on static, independent recall and fail to capture these dynamic interactions between evolving memories. In this paper, we study how current memory-augmented agents perform in realistic, interference-heavy, long-horizon settings across diverse domains and question types. We introduce MINTEval (Long-Horizon Memory under INTerference Evaluation), a benchmark featuring (1) long, highly interconnected contexts with frequently updated information that induces substantial interference, (2) diverse domains (state tracking, multi-turn dialogue, Wikipedia revisions, and GitHub commits), enabling evaluation of domain generalization, and (3) diverse question types that assess robustness to interference, including (i) single-target recall tasks requiring retrieval of a specific target from long contexts, and (ii) multi-target aggregation tasks requiring reasoning over multiple relevant pieces of information. Overall, MINTEval has 15.6k question-answering pairs over long-horizon contexts averaging 138.8k tokens and extending up to 1.8M tokens per instance. We evaluate 7 representative systems, including vanilla long-context LLMs, RAG, and memory-augmented agent frameworks. Across all systems, we observe consistently low performance (avg. 27.9% accuracy), especially on questions requiring aggregated reasoning over multiple pieces of evidence. Our analysis shows that performance is primarily limited by retrieval and memory construction. Furthermore, current memory systems struggle to recall and reason over earlier facts that are revised or interfered with by subsequent context, with accuracy degrading as the number of intervening updates increases.

新论文 · v1arXiv:2611.26514

Hybrid Retrieval for Government Scheme Search in English and Marathi

Aishwarya Gunjal, Kanchan Khemnar, Pawan Poojary, Pranav Kulkarni, Raviraj Joshi, Manish Khodaskar

原文摘要

Retrieving government schemes requires matching citizens' information needs to formal administrative descriptions, often across languages and terminology. We present a bilingual search system for Maharashtra government schemes and public services that combines BM25 retrieval with sentence-embedding similarity through equal-weight score fusion. The system indexes aligned English-Marathi scheme descriptions and supports multilingual, Marathi-focused, and translation-mediated semantic configurations. Evaluation on manually curated bilingual queries compares BM25, dense retrieval, and hybrid retrieval using IndicSBERT and MahaSBERT. BM25 provides a strong baseline with a mean reciprocal rank (MRR) of 0.864. Hybrid retrieval increases MRR to 0.872 with IndicSBERT and 0.879 with MahaSBERT, whereas the corresponding dense-only systems achieve 0.663 and 0.655. MahaSBERT-based fusion also increases precision from 0.781 to 0.808 while matching BM25 recall at 0.946. These results support the complementary use of lexical and semantic signals in this collection, while showing that improvements over a strong lexical baseline are modest and metric-dependent. The study provides an application-focused analysis of hybrid retrieval for bilingual public-service information access.

cs.LG · cs.CL

新论文 · v1arXiv:2611.26510

AutoMaster:通过让同一模型成为更好的教师实现自主后训练

AutoMaster: Autonomous Post-Training by Making the Same Model a Better Teacher

Guoxin Chen, Shuang Sun, Fanzhe Meng, Xinyu Tang, Ruihua Song, Wayne Xin Zhao

AI 速读 基于摘要

AutoMaster 利用自然语言技能引导教师模型生成更优轨迹,并通过 LLM 智能体自主设计干预,从而提升目标模型的后训练效果。

cs.CL

查看原文摘要

Task success alone does not specify which behaviors post-training should reinforce. Even successful teacher trajectories can contain unsupported assumptions, unproductive repetition, or superficial verification. We propose Skill-FT (Skill-Guided Fine-Tuning), which uses natural-language skills to suppress undesirable habits and elicit underrepresented effective behaviors during teacher rollouts, then fine-tunes a target model on the resulting trajectories. We introduce AutoMaster, an autonomous post-training system in which an LLM agent develops these interventions through trajectory analysis, skill design, data selection, and feedback from rollouts and target-model evaluation. Across Terminal, Search, and software engineering tasks with 4B and 9B target models, AutoMaster improves mean performance over Vanilla SFT on successful unguided teacher trajectories by 1.42-8.99 percentage points, with the teacher, task pool, training set size, and SFT recipe held fixed. Together with the ablations and trajectory analyses, these results suggest that behavioral shaping can make a fixed model a more effective teacher. We further find that retaining skill instructions during SFT yields higher mean performance than removing them across all six settings, despite their absence at evaluation and identical supervised outputs. These findings suggest that preserving skill context as part of a training demonstration can support better behavioral internalization.

新论文 · v1arXiv:2611.26509

GLiDE:从推理教师模型蒸馏得到的快速、校准决策模型

GLiDE: A Fast, Calibrated Decision Model Distilled from Reasoning Teachers

Sahibzada Allahyar, Julia White, Dhruv Atreja, George Hurn-Maloney, Urchade Zaratiana

AI 速读 基于摘要

GLiDE 是一系列通过软目标蒸馏和渐进式后训练从推理教师模型学到的决策模型,能在单次前向传播中快速、校准地评分候选答案,无需生成文本或推理过程。

cs.AI · cs.CL

查看原文摘要

Decision models enable fast, confidence-aware decisions by scoring candidate answers in a single forward pass, without generating text or intermediate reasoning. Yet reasoning can substantially improve decision quality, raising the question of whether its benefits can be retained without the cost of generating it. We investigate this question with \textbf{GLiDE}, a family of decision models spanning 0.4B to 27B parameters. Building on Qwen hybrid language models, GLiDE enables bidirectional interactions between the context, question, and candidate answers by removing causal masking from full-attention layers. To transfer reasoning capabilities into single-pass inference, we combine soft-target distillation from multiple teachers, including a reasoning model, with progressive post-training on diverse decision tasks. We further explore parameter-free recurrent depth to increase inference-time computation without generating tokens. Across five model sizes, GLiDE lies on the performance--parameter Pareto frontier of the Hugging Face \DI{}, with each model outperforming evaluated alternatives of equal or smaller size. \dmtwo{} (27B) achieves a hidden-set score of 71.52, with an expected calibration error of 2.0\% and a median latency of 92.9\,ms on a single GPU. Further checkpoint averaging and parameter-free recurrent depth yield GLiDE~27B, which reaches 73.37 with an expected calibration error of 2.1\%.

版本更新 · v2arXiv:2609.38169

STEPQuant:Delta规则循环状态量化中误差何时何地重要

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

Bingchen Yao, Haobo Xu, Haokun Lin, Yichen Wu, Ziyu Guo, Renrui Zhang, Zhichao Lu, Zhenan Sun 等 9 位作者

AI 速读 基于摘要

STEPQuant 是一种面向 Delta 规则循环状态的空间-时间训练后量化框架,依据误差大小与内存寿命分配精度,并联合拟合键行与值列缩放。

cs.CL · cs.AI · cs.LG

查看原文摘要

Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck under concurrent serving. Directly quantizing recurrent states to low precision often leads to severe accuracy degradation, as quantization errors propagate through successive state updates. We discover that the impact of these errors depends on two complementary dimensions: temporally, errors in long-lived memory can persist across many decoding steps; spatially, errors in different key rows affect model outputs differently, while state magnitudes vary substantially along both rows and columns. Motivated by these observations, we propose STEPQuant, a spatial-temporal post-training quantization framework for Delta-rule recurrent states. STEPQuant allocates precision according to error magnitude and memory lifetime, and jointly fits key-row and value-column scales based on state distributions and key-row impact on output error. Experiments on Qwen3.8-27B and Kimi-Linear-48B-A3B-Instruct across both long- and short-generation benchmarks show that STEPQuant closely matches FP32-state accuracy under a nominal 6-bit budget and outperforms uniform INT8 in its 4-bit configuration. Integrated into SGLang with optimized GPU kernels, 6-bit STEPQuant achieves over 5x recurrent-state compression and reduces total serving memory by up to 68.7%. Our code is available at https://github.com/Dreamer-Toby/STEPQuant.

版本更新 · v2arXiv:2605.13451

LongBEL: Long-Context and Document-Consistent Biomedical Entity Linking

Adam Remaki, Xavier Tannier, Christel Gérardin

原文摘要

Biomedical entity linking maps textual mentions to concepts in structured knowledge bases such as UMLS or SNOMED CT. Most existing systems link each mention independently, using only the mention or its surrounding sentence. This ignores dependencies between mentions in the same document and can lead to inconsistent predictions, especially when the same concept appears under different surface forms. We introduce LongBEL, a document-level generative framework that combines full-document context with a memory of previous predictions. To make this memory robust, LongBEL is trained with cross-validated predictions rather than gold labels, reducing the mismatch between training and inference and limiting cascading errors. Experiments on five biomedical benchmarks across English, French, and Spanish show that LongBEL improves over sentence-level generative baselines, with the largest gains on datasets where concepts frequently recur within documents. An ensemble of local, global, and memory-based variants achieves the best results across all benchmarks. Further analysis shows that the largest gains occur on recurring concepts, suggesting that LongBEL mainly improves document-level consistency rather than isolated mention disambiguation.

cs.CL

版本更新 · v3arXiv:2609.19153

Stop Removing Stopwords: How an Inherited Preprocessing Default Distorts Legal Text-as-Data

Gregory M. Dickinson

原文摘要

Empirical legal scholarship increasingly treats judicial text as data, and much of it still runs on sparse, interpretable pipelines -- TF-IDF features and linear classifiers -- because the textual feature is often the object of study rather than a means to prediction. Yet these pipelines inherit preprocessing defaults from mid-century information retrieval that were never validated against classification accuracy. The most entrenched of these is stopword removal. This study introduces an exhaustive single word ablation that measures the effect of a preprocessing step directly against the downstream objective, and applies it to stopword removal as the hardest case to dislodge. Matching Supreme Court Database labels to Caselaw Access Project opinion texts, the study examines two binary tasks that bracket F1 headroom, ideological direction (no-removal baseline F1 ~0.68) and constitutional versus non-constitutional law type (~0.92), across 7,668 and 7,001 opinions. For each task, the ablation removes each of about 18,500 candidate words in turn, and a task-specific stoplist is built from the measurements. Common generic stoplists fall below the no-removal baseline in all twelve held-out tests. The task-specific stoplists move held-out F1 by +0.0023 (95% CI [-0.0124, +0.0170]) on ideology and by +0.0001 ([-0.0082, +0.0085]) on law type. Neither task shows a detectable benefit from removal, and supplemental analysis finds that word-level statistics predict removal effects poorly, because true removal effects differ by less than the measurement can register, leaving little to predict. The method generalizes to any inherited preprocessing default; the result is a caution specific to interpretable legal text-as-data, where a step that reshapes which features a model sees can distort the doctrinal and ideological signal the research is meant to recover. The burden of proof sits with removal.

cs.CL · cs.CY · cs.IR · cs.LG

版本更新 · v4arXiv:2608.30044

Balance of Benchmarks: Evidence Retention and Multiplicity-Aware Model Comparison

Jhen-Ke Lin, Hong-Yun Lin

原文摘要

Benchmark aggregation requires decisions about how much evidence to use and how much influence each benchmark receives. Curated suites control influence through selection, which can exclude informative observations. A broader pool can retain those observations. With equal weighting, repeated or closely related benchmarks gain influence as their number grows. We introduce Balance of Benchmarks (BoB) to retain eligible observations and control their influence separately. We fit benchmark-specific response curves to place different difficulty ranges on a shared ability scale and use description similarity to downweight benchmarks in crowded neighborhoods. We test retention and density weighting in separate interventions on WildScores, a sparse collection of 148 developer-reported benchmarks, using 14 Artificial Analysis benchmarks as a controlled reference. With the model population fixed and entire source-lineage families held out, suite expansion improves held-out prediction under BoB and equal-weight equating on both WildScores and BIG-bench. Under substantial reporting overlap, density weighting improves robustness to multiplicity. Complete re-listings yield smaller mean rank displacement under BoB (0.63 versus 1.95 for equal-weight equating), with benefits also in paraphrased re-listings and supported affine fits. The benefit can reverse if models report different benchmarks, because a single weight per column gives models that report only part of a group less than its intended share. We therefore compute each model's weights from the benchmarks it reports. This rule removes the reversal in controlled re-listings and keeps held-out prediction close to that of equal weighting. These comparisons separate evidence retention, benchmark influence, and reporting coverage and show why repeated entries need to be handled per model.

cs.AI · cs.CL · cs.LG

新论文 · v1arXiv:2611.26398

Democratizing Cross-Project Knowledge for Transforming Water Governance and Climate Resilience: an Agentic AI Ecosystem

Oriol Alàs, Ian Palacín, Iván Cester, Edgar Rubión

原文摘要

EU-funded projects produce extensive evidence in the form of deliverables, reports, and case studies. However, this knowledge is typically scattered across projects and document structures, making it difficult to locate relevant, contextual information when making decisions. This paper introduces an Agentic AI Ecosystem that consolidates heterogeneous project documentation into a domain-aware knowledge base and provides adaptive access through an agentic Retrieval-Augmented Generation pipeline. Documents from three EU-funded projects (IMPETUS, NATALIE, and InnWater) are reconstructed into hierarchical section trees and indexed with structured metadata. Retrieval is supported by two domain-specific embedding models fine-tuned on domain data (water and climate). On top of this knowledge base, a ReAct-style controller iteratively orchestrates retrieval actions by allocating retrieval budget across domain collections and accumulating evidence until a stopping criterion is met. In a retrieval benchmark over the corpus, the proposed approach improves Mean Reciprocal Rank by 26.7% (relative) compared to a single-domain embedding baseline, indicating more consistent retrieval of relevant evidence to support cross-project knowledge synthesis and climate-resilient decision-making.

cs.IR · cs.AI · cs.CL

版本更新 · v2arXiv:2611.23035

Storing the Gemma 4 K=V Cache Once: Exact Global-KV Memory Savings in a Paged Serving Engine with Unchanged Attention Kernels

Kushagra Bainsla

原文摘要

In the global attention layers of Gemma 4 31B, the value is the normalized key projection, and the key is the value scaled by a fixed weight, with rotary position encoding on one quarter of its dimensions. The Gemma 4 report states that this design reduces the global KV cache by up to 37.5%, but the open serving engines that we checked still store a full key and a full value: 1,024 values per KV head and token. We store one 640-value row instead, exact in real arithmetic, and an unchanged paged attention kernel reads it through two overlapping strided views as its key cache and its value cache. In a vLLM prototype with the 16-bit 31B model, the outputs are bit-identical to an emulation of the same arithmetic on the stock cache, 2 of 432 final answers differ from the stock engine (within its run-to-run noise), and the steady decode KV memory per request falls by a factor of 1.34 to 1.40 at 32K to 64K tokens. On a prefill/decode pair of two A100 GPUs with NIXL transfer and CPU offload, a decode engine with a full 15 GiB pool ran 1.38 times the stock decode tokens per step for 16K-token prompts (repeated to 0.06%) and 1.24 times for 8K-token prompts; a model of the vLLM block pool predicted both ratios to within 1% (the engine was 0.7% to 0.9% higher) and matched the change between them. The eager decode throughput rose by 1.30 and 1.11 times, and on this path the compact engine gave the same output tokens as the emulation for 8 prompts at batch 1. The run-time prototype makes an eager step 4% to 9% slower at equal batch, and the method does not yet stack with an 8-bit KV cache at the default scale.

cs.LG · cs.CL · cs.DC

新论文 · v1arXiv:2611.26358

Beam Model Technical Report

Reflection Team, Adam Abdulhamid, Osama Abuelsorour, Yasmin Alameddine, Carlo Alfano, Duarte Alves, Brandon Amos, Selvaraj Anandaraj 等 230 位作者

原文摘要

Beam is a sparse Mixture-of-Experts (MoE) model with 501.3B total parameters and 23.4B active parameters, specifically built and optimized for coding, reasoning, and agentic workloads. Beam delivers frontier level reasoning, while requiring 3-4x less inference compute than many models of its class. Pretrained on 23.8T diverse, curated, high-quality tokens, Beam features a 1M-token context window achieved through a novel two-stage midtraining phase, built on verifiable, correctness-anchored data. Post-training leveraged a large-scale, fully asynchronous reinforcement learning (RL) campaign across 10.5K GB300 GPUs, generating over 100M rollouts over 4 weeks of training. We believe this is one of the largest scale RL runs conducted by any open lab to date. Across our evaluation suite, capabilities continued to improve as we increased RL compute, with no sign of a plateau. Supported by deep hardware-model co-design, FP8/NVFP4 quantization, and a 1.93B-parameter speculative decoding drafter (DFlash 2), Beam maximizes serving throughput with efficient, flexible deployment. Averaged across conversation turns and harm categories, Beam refuses or pivots on 88.9% of harmful requests while complying with 81.5% of harmless requests, achieving the highest refusal/pivot rate on harmful requests among open-weight models on the Pareto frontier.

cs.CL · cs.AI

版本更新 · v2arXiv:2611.18714

How to make a moral agent: sentimentalism and rationalism as lenses on AI

David Gottlieb, Jared Moore

原文摘要

Can AI systems be moral agents? That is, can they undertake actions that can be correctly assessed as morally right or wrong? There is no settled normative criterion of moral agency that applies neatly outside paradigm human cases. Because of the difficulties with a normative account, we instead propose a research program to explore descriptive moral agency. Most basically, we ask, what are the capabilities we humans possess that underlie our moral agency? To do so, we draw on historical scholarship in philosophy and moral psychology to isolate candidate capabilities. Then we suggest refining candidate capabilities so that they are testable in the context of AI systems. Finally, we offer specific empirical recommendations to test AI systems, especially large language models (LLMs), for those refined capabilities. Our approach offers several benefits. Firstly, it may demonstrate whether the behaviors of AI systems are aligned, or in a broad sense desirable. Secondly, the debate may inform policy questions (e.g., what models should be deployed in which contexts?). Thirdly, our approach may complement engineering and design efforts: when capabilities can be precisely characterized, they can inform the development of models. Fourthly, applying our moral reasoning concepts in the new context of AI systems should improve our understanding of those concepts.

cs.AI · cs.CL

新论文 · v1arXiv:2611.26336

One Framework to Diagnose Them All: A Stratified Benchmark for Bengali LLM Hallucination

Asif Shahriyar Sushmit, Shefayat E Shams Adib, Abdullah Al Jubaer Gem, Ahmed Shafin Ruhan, MD. Nazmuddoha Ansary, Biplab Kumar Sarkar, Syed Rifat Raiyan, Ajwad Abrar 等 19 位作者

原文摘要

Hallucination research in low-resource languages fragments easily: each newly named failure mode prompts its own dataset, spending scarce annotators on incomparable resources. We argue for consolidation and test it at community scale. Alikbachan is a Bengali hallucination-detection benchmark stratified along three crossed axes: a human-validated cultural-distance band, six task types, and a five-family, 32-mode hallucination taxonomy. It comprises a harvested 2,516-item test set (Phase 1) and a quota-constructed, gold-labeled 5,000-item set (Phase 2). The stratification is diagnostic. Four zero-shot LLM judges vary by over 30 macro-F1 points across strata, and the item-level predictions of 99 Phase-1 and 32 Phase-2 competition systems reproduce the profile: discourse-level omission defeats judges and most teams alike, whereas only a minority over-flag negative controls. The judges' verdict probabilities rank items well (ROC-AUC 0.74-0.95) but are overconfident (ECE 0.04-0.29). An open competition on Alikbachan drew 222 teams and 3,566 submissions, and a single-prompt 32B judge reaches the 57th percentile. Of the 25 teams in both phases, 24 regress on Phase 2 (mean $-17.6$ points) while every zero-shot judge improves, and Phase-1 rank barely predicts Phase-2 rank (Spearman $ρ=0.35$), so a Phase-1 leaderboard alone would have crowned a different winner.

cs.CL · cs.AI

版本更新 · v2arXiv:2604.03257

Robust LLM Evaluation with Boundedly Bad Judges: A Constrained Maximum Likelihood Approach

Minghe Shen, Ananth Balashankar, Adam Fisch, David Madras, Miguel Rodrigues

原文摘要

Evaluating language models at scale often involves reconciling costly, but reliable, labels (e.g., from human raters) with cheap, but noisy, proxy labels (e.g., from LLM-as-a-judge autoraters). This paper proposes constrained maximum likelihood estimation (CMLE), a likelihood-based approach to large language model (LLM) evaluation that explicitly models the error in the proxy labels via their true-positive and false-positive rates, subject to data-driven constraints. Functionally, these constraints act as an adaptive regularization that restricts the feasible judge error rates, particularly when the available number of reliable labels is limited. In contrast to asymptotically unbiased estimators (such as those based on prediction-powered inference), this formulation accepts a controlled bias under misspecified constraints in exchange for variance reduction relative to various baselines including unconstrained maximum likelihood estimation (UMLE); we characterize this bias--variance tradeoff analytically under point constraints. We identify the regimes in which CMLE outperforms UMLE and prediction-powered baselines in mean squared error. We further extend the framework to heterogeneous settings using a stratified variant involving stratum-specific constraints based on judge confidence. Empirically, on synthetic and real-world LLM evaluation tasks, CMLE achieves up to roughly 9\% lower mean squared error (MSE) than non-stratified baselines, and its stratified variant (SCMLE) achieves up to roughly 30\% lower MSE than the strongest baseline considered, with the largest gains in low-label regimes.

cs.CL · cs.AI

版本更新 · v2arXiv:2607.22610

Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations

Jessica Tang, Shraddha Barke, Sharad Agarwal

原文摘要

When a model answers after several turns of dialogue and tool use, an overseer needs to know which earlier turns and intermediate steps it rests on. Attribution is the natural primitive for answering this, but existing context attribution methods process the full transcript in a single pass: they recover surface-level dependencies while missing the layered structure of multi-turn traces, in which an assistant turn is itself a derived artifact that condenses or transforms earlier context. We introduce multi-turn context attribution (MTCA): given a target span in a model response, the task of tracing attribution backward across turns to identify not only which prior turns were directly relevant, but also how those turns themselves depended on earlier context. We propose Tokengeist, an attribution-method-agnostic and scalable framework that recovers full dependency paths by casting attribution as a recursive traversal of a directed acyclic graph over conversation turns. We will release MTCABench, a benchmark of 3,970 target spans across 685 multi-turn conversations, annotated with gold provenance graphs reaching depths of up to 17, across four dependency types. Across four open-weight models, flat attribution methods fail to recover multi-hop dependencies, with source recall improving from 11-38% under flat attribution to 82-94% under Tokengeist. Our results reveal a systematic failure mode of single-pass attribution, which we term provenance collapse, where attribution terminates at the nearest assistant restatement instead of the originating event.

cs.AI · cs.CL

版本更新 · v2arXiv:2610.21062

SnapJudge: Multimodal AI Detection for Math-Heavy Scientific Text

Yixuan Huang, Danish Pruthi, Bhuwan Dhingra

原文摘要

As large language models become increasingly capable of generating, and assisting with, scientific writing, there is a need for greater transparency and disclosure around the use of AI in research. Consequently, a veritable subfield of research and a number of commercial services aim to flag AI-generated content automatically. However, existing detectors which rely only on text extracted from PDFs fail to benefit from the rich visual information contained in the formatting of math-heavy scientific content. To study this, we select human-written proof and prose passages from pre-2022 arXiv LaTeX sources and re-generate them using 15 modern LLMs within the context of the same paper. This leaves us with coupled human and AI outputs in three different representations: the LaTeX source, a rendered image of the PDF, and the text extracted from the PDF. We find that the accuracy of the state-of-the-art Pangram 4 drops significantly as the mathematical content in a passage increases, especially when evaluated on text as opposed to LaTeX. However, this is not an inherent limitation of detecting AI-generated math: finetuning Qwen-3.5-27B based detectors on this domain recovers the gap, with LaTeX inputs performing significantly better than text since they preserve more formatting information. Since LaTeX sources are rarely available in practice, we also train SnapJudge: an image-based detector operating on screenshots of both prose and proofs from papers. At 0.1% false positive rate, SnapJudge achieves a detection rate of 92% on proofs and 93% on prose generated by frontier models, substantially outperforming both Pangram 4 and our text-based detector. We release our data, models and code at https://nlplab.cs.duke.edu/snapjudge.

cs.CL

新论文 · v1arXiv:2611.26317

Language-Oriented Semantic Modeling for Target Language Extraction

Mehmet Sinan Yıldırım, Ke Zhang, Shuai Wang, Haizhou Li

原文摘要

Target Language Extraction (TLE) aims to isolate speech in a target language from multilingual mixtures. Existing approaches primarily rely on acoustic modeling with language identity labels, which provide only coarse categorical guidance. In this work, we propose a language-oriented semantic modeling framework that augments acoustic extraction with language-specific semantic representations. A pre-trained speech semantic model is adapted via language-aware prompt conditioning and parameter-efficient fine-tuning to generate target-language-focused semantic representations from the mixture. {These capture high-level semantic structure of the acoustics and they} are integrated into the extraction model to provide structured semantic guidance beyond identity labels. Experiments on the CommonVoiceMix dataset show that incorporating semantic representations consistently improves over acoustic-only baselines, achieving up to 1.16 dB SI-SDR gain.

cs.CL · eess.AS

版本更新 · v3arXiv:2606.00384

VESTA: Visual Exploration with Statistical Tool Agents

William Rudman, Abhishek Divekar, Kanishk Jain, Sebastian Joseph, Stella S. R. Offner, Matthew Lease, Kyle Mahowald, Greg Durrett 等 9 位作者

原文摘要

Fitting quantitative models to data is a central step in scientific workflows, yet it remains one of the least automated. Recent agent-based systems leverage language and vision-language models (VLMs) to propose statistical models, but these systems struggle on challenging modeling tasks. To address these limitations, we introduce VESTA (Visual Exploration with Statistical Tool Agents), a framework that equips VLMs with a dynamically growing toolkit to guide model refinement through data transformations, hypothesis-driven visualizations, and statistical tests. Unlike prior systems that rely on iterative critique alone, VESTA explores data before and during refinement by selecting or creating reusable diagnostic tools. We evaluate VESTA using three toolkit configurations: no tools, static expert-written tools, and dynamic model-written tools. To support this evaluation, we introduce DAWN (Dataset for Automated Workflows and Numerical Modeling), a benchmark targeting distribution fitting and time series modeling with varying difficulty tiers that culminates in real-world astronomy tasks including modeling initial mass functions and gravitational-wave chirp signals. VESTA's dynamic tool creation outperforms prior agentic pipelines for statistical analysis and visual tool creation, with the largest gains on complex and domain-specific tasks. Against strong agentic coding harnesses (Claude Code, Codex, and OpenCode), VESTA is better on all time series tasks and on complex distribution fitting tasks, though the harnesses achieve better fits on simpler distributions. Further, dynamically generated tools are substantially more sophisticated than those produced by existing visual tool-creation systems, covering more diagnostic categories per function and strongly preferring visual outputs that the VESTA VLM critic can reason over directly.

cs.AI · cs.CL · cs.CV · cs.LG · stat.CO

新论文 · v1arXiv:2611.26282

What If Chain-of-Thought Is Not Enough?

Marc Jansen

原文摘要

Reasoning capabilities in large language models have evolved from prompting-based methods to internalized model behaviors. In this paper, we investigate whether the internal thinking model of an LLM can be deliberately changed and whether such a change is beneficial. Instead of relying on Chain-of-Thought, we train models to follow Question--Option--Criteria (QOC), a structured decision process that decomposes a task into explicit questions, competing options, and evaluation criteria. We present a three-generation development pipeline that ranges from a basic QOC decision core to richer answer synthesis and statistically enriched QOC reasoning. We then evaluate the resulting models with respect to both internal consistency and output quality. Across the reported experiments, QOC-based fine-tuning improves answer quality relative to non-fine-tuned base models and yields particularly strong gains once models are large enough to execute the underlying QOC computations reliably. The results suggest that the internal thinking model of an LLM is trainable and that structured alternatives to Chain-of-Thought can provide a promising path toward more reliable, interpretable, and task-adapted decision support.

cs.CL · cs.AI

版本更新 · v2arXiv:2611.00172

From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings

Ziyin Zhang, Yuyu Guo, Ying Zhang, Siqiao Xue, Zihan Liao, Jin Qin, Wenjie Yang, Siyuan Yang 等 18 位作者

原文摘要

Embedding models underpin virtually every modern AI system, from search engines to recommendation systems. Despite shared mathematical foundations, research on embedding models remains fragmented by modality: the communities develop largely in isolation, seldom exchanging insights. We argue that this fragmentation obscures a deeper convergence. Driven by contrastive learning, Transformer architectures, and a granularity shift, embedding research across modalities is converging toward a common set of principles, even as modality-specific challenges remain underexplored. To reason across this convergence without conflating it, we propose a framework of three progressively harder capabilities: coverage, comparability, and compositionality. Three paths toward unification satisfy these in turn: transformation broadens coverage, alignment enables comparability, and joint embedding, the terminus we advocate, aims at compositionality. This position paper traces the resulting evolution, providing the first unified, cross-cutting treatment of omnimodal embedding research.

cs.CL · cs.AI

新论文 · v1arXiv:2611.26255

STAGE: Spatio-Temporal Augmented Graph Expansion for Weakly Supervised Cross-Tweet Event Causality Discovery

Hieu Minh Duong, Todd Gary, Eugene Levin, Long Nguyen

原文摘要

Causal relations in disaster-related social media of- ten span independent posts, making cross-tweet causal discovery difficult to supervise and model at scale. We propose STAGE, a framework that separates scalable cross-tweet weak-supervision construction from spatio-temporal relational learning over event occurrences. Starting from local causal seeds, STAGE retrieves semantically related event occurrences across tweets and uses a causal scorer to construct weakly labeled cross-tweet pairs. These pairs supervise a multi-head Graph Attention Network over semantically enriched event representations and a spatio- temporal context graph. We evaluate STAGE on California Wildfire and Hurricane Harvey using human-gold cross-tweet test sets and 15 baselines. Compared with local-only supervision, the constructed cross-tweet supervision improves STAGE AUPRC by 0.340 on Wildfire and 0.107 on Hurricane. STAGE achieves in-domain AUROC of 0.885 on Wildfire and 0.710 on Hurricane. Cross-disaster experiments reveal asymmetric transfer, highlighting sensitivity to dataset-specific spatio-temporal shifts. These results demonstrate the value of scalable cross-tweet supervision combined with relational event modeling for causal learning across fragmented disaster reports.

cs.CL · cs.AI