跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 05:07 · 全站最近入库：2026-11-08 06:02各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 06:02 — 2026-11-09 06:02（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：2026-11-09 05:07最近发现新增版本：2026-11-08 06:02库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,057 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 5,059 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 05:05（北京时间）
版本更新 · v2arXiv:2605.07139

Structural Rationale Distillation via Reasoning Space Compression

Jialin Yang, Jiankun Wang, Jiajun Wu, Henry Leung, Jiayu Zhou, Steve Drew

原文摘要

When distilling reasoning from large language models (LLMs) into smaller ones, teacher rationales for similar problems often vary wildly in structure and strategy. Like a chef who makes the same dish differently each time, this inconsistency burdens the student with noisy supervision that is hard to internalize. We propose Distillation through Reasoning Path Compression (D-RPC), which constrains the teacher to follow a compact, dynamically maintained bank of reusable high-level reasoning paths. For each training question, D-RPC retrieves the most relevant path and conditions the teacher to follow it, producing rationales that are consistent across similar problems yet diverse enough to cover different problem types. A PAC-Bayes analysis formalizes a trade-off between bank size and coverage, with smaller banks limiting path diversity at the risk of coverage gaps. Our ablations favor an intermediate bank size, consistent with this trade-off. Across five math and commonsense reasoning benchmarks with two student models, D-RPC achieves the highest average accuracy among the evaluated distillation methods, while using fewer tokens than template-heavy alternatives.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.11746

Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization

Ellen Su, Andres Potapczynski, Shikai Qiu, Edward Hughes, Andrew Gordon Wilson

原文摘要

Modern systems are increasingly expected to transfer across tasks not specified during training. What data facilitates generalization to unanticipated settings? One hypothesis is that data with more structural information could contain shared circuits and subprograms that may be recycled in a wider array of downstream settings. Epiplexity, a recently proposed measure of the structural information a compute-bounded learner can extract from data, offers a mechanism to reason about this relationship. As existing estimators for epiplexity only operate on data already seen during training, we show how to operationalize epiplexity as an online training signal by greedily maximizing its stepwise gain in two settings. For data selection, we fit scaling laws to the training loss curves of natural data domains to predict the expected epiplexity gain as a function of training tokens, and use this signal to adaptively determine the sampling weights over domains during training. For synthetic data generation, where no domain structure exists, we reward a generator with the change in epiplexity of a learner's synthetic training data and use REINFORCE policy gradients to guide the generator toward an epiplexity-maximizing distribution. In both cases, we find higher epiplexity predicts improved downstream performance on zero-shot and fine-tuning tasks, supporting the hypothesis that data rich in structural information yield representations that better transfer across domains.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.27262

Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs

Md Tahmid Rahman Laskar, Xue-Yong Fu, Shashi Bhushan TN

原文摘要

Production customer-support systems often require LLMs to support multiple skills, such as intent classification, question answering, summarization, or tool-use decisions. A central deployment question is whether these skills should be handled by separate task-specialist models or by a single model trained through multi-task training, sequential updates, or model merging. We study this question using thirteen models spanning five families (Qwen3, Qwen3.5, Gemma-3, Llama-3.1, and Mistral) from 0.6B to 32B parameters across eight customer-support datasets, spanning four public and four proprietary datasets with approximately 74.5k training and 8.7k evaluation samples. Under a fixed training protocol, we train more than 200 checkpoints. Our experiments reveal that multi-task full fine-tuning is the strongest operational default at every model size we test. Specialist models are strong on their target tasks but often degrade sharply off-task, making reliable routing important. Sequential Low-Rank Adaptation (LoRA) preserves earlier skills better than sequential full fine-tuning, while merging a specialist with its base model improves off-task robustness with limited same-task loss for larger models. We conclude with practical guidelines for selecting fine-tuning strategies in real-world settings.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05827

TandemBench: Benchmarking Decision Models for Multi-Agent Collaboration

Baohang Li, Xiaocheng Feng, Bing Qin

原文摘要

Decision models choose among predefined options in tasks such as routing and action selection. In multi-agent collaboration, a decision determines how members divide work, exchange resources, and act in parallel. We introduce TandemBench, a benchmark of 1,200 questions in multi-agent cooking scenarios where coordination choices affect goal completion. Models receive complete global information and candidate team plans, with reference answers established through execution and exact search. Models select an optimal team plan and, in paired variants that retain or remove it, judge whether better arrangements exist beyond the supplied options. We evaluate 40 native decision models and compare them with 10 general-purpose language models. The best native decision model achieves 62.50% decision accuracy. Native decision models remain close to chance in optimality verification. Paired tests reveal that some report better alternatives regardless of whether an optimal plan is already present. These findings show that team-plan decision accuracy alone can conceal systematic errors in judging whether the supplied options contain an optimal arrangement. The dataset and evaluation code are publicly available at https://github.com/lililibaohang/TandemBench.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05814

Learning When Human Decisions Matter: Executor-Relative Consultation Value for LLM Agents

Shuli Jiang, Khushbu Pahwa, Yuting Zhang, Yi Zhang, Wei Xia, Stefano Soatto

原文摘要

Large language models increasingly automate complex tasks, but human decision capacity does not scale with their capabilities. In many applications, humans remain essential for providing private context, authority, or judgments unavailable to the agent. We formulate human decision capacity allocation: given multiple consultation opportunities and a limited budget, at which decisions should an LLM agent consult a human? The central challenge is estimating consultation value, which is executor-dependent because the same human input may benefit different downstream agents differently. We introduce Consultation Value Distillation (CVD), which estimates consultation values offline using Monte Carlo executor rollouts and distills these values into lightweight predictors for budgeted allocation, requiring no rollout-based value estimation at deployment. Across five batch and three sequential settings with two frontier executors, CVD improves allocation through joint and continuation-aware value learning, while independent consultation values remain competitive in several settings. CVD also broadly outperforms direct prompting and Value of Information where applicable, remains robust with substantially less rollout supervision, and enables nearly lossless approximate allocation at low search cost.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00935

Labadain-MedQA: A Tetun Medical QA Dataset for Fine-Tuning and Evaluating Large Language Models

Gabriel de Jesus, Sérgio Nunes

原文摘要

Advances in large language models (LLMs) have created opportunities for cross-lingual transfer of medical knowledge from high-resource to low-resource languages to support access to healthcare information. However, medical question-answering (QA) datasets for fine-tuning and evaluating LLMs remain scarce for Tetun. To address this gap, we translated MedAlpaca's Medical Flashcards and WikiDoc Patient Information collections into Tetun using Gemini 2.5 Flash, producing 39,077 medical QA pairs. Translation quality was assessed on 50 randomly sampled QA pairs (100 documents) using automatic metrics against human reference translations and evaluations by two native Tetun-speaking healthcare professionals, focusing on medical accuracy and Tetun fluency. Human translations achieved higher mean ratings than LLM-generated translations for both criteria (4.43/5 vs. 4.02/5), with statistically significant differences (Wilcoxon signed-rank test, p < 0.001). To assess downstream utility, we fine-tuned Gemma and Llama variants on the translated MedAlpaca dataset using parameter-efficient fine-tuning (PEFT) and evaluated them on 325 Tetun-translated United States Medical Licensing Examination multiple-choice questions. Gemma 4 12B fine-tuned using QLoRA achieved relative improvements in mean accuracy of 10.79% with 4-bit NormalFloat (NF4) inference and 10.42% after merging the LoRA adapters into the BF16 base model, compared with the corresponding base models. These results highlight the viability of automatic dataset translation for Tetun medical QA and the effectiveness of PEFT in enhancing model performance. The datasets, models, and evaluation resources are accessible at https://github.com/labadain/labadain-medqa to support reproducible research on Tetun medical QA and facilitate machine translation, cross lingual, and multilingual research.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.01825

The Scope Grammar of Natural-Language Rules: Counting and Enumerating Readings modulo Logical Equivalence

Sherzod Turaev

原文摘要

A rule written for people fixes its atomic conditions and connectives but leaves open how the connectives are bracketed, and each bracketing is a different logical reading that an autoformalizer must resolve or expose. We study the scope grammar, a deliberately ambiguous context-free grammar whose derivation trees are the readings of a connective skeleton and whose quotient by logical equivalence is what matters downstream. A skeleton with $k$ binary connectives has $C_k$ derivation trees, the $k$-th Catalan number, but far fewer logically distinct readings. For the positive, repetition-free fragment we make the gap exact: through the uniqueness of the read-once normal form we characterize the realizable normal forms by lowest common ancestors and count them with a two-label recurrence over the operator word, verified against exhaustive enumeration up to eleven atoms. The count is invariant under reversal and $\wedge/\vee$ duality; a skeleton is ambiguous if and only if it uses both $\wedge$ and $\vee$, a one-pass test; and the number of classes is at least $2^{\lfloor n/3\rfloor}$. Up to fifteen atoms the alternating pattern is the worst case; its count has a cubic generating function, is the 3-Schröder sequence (OEIS A137842), and grows with base $\varphi^{5/2}\approx3.330$, below the Catalan base 4. We reduce maximality to an inequality on increments, verified to sixteen atoms, and explain why local exchange arguments cannot prove it. We also treat negation, exceptions, and background axioms, where normal-form uniqueness still decides equivalence but counting is open.

cs.FL · cs.CL · cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.11460

Principal Trait Analysis: Identifying User Behavioral Traits in Human-AI Collaboration

Hunter McNichols, Fareya Ikram, Kai Du, Andrew Lan

原文摘要

Human-artificial intelligence (AI) collaboration takes many forms and occur in both professional and educational scenarios. It is important to identify how human users interact with AI and how their behavior affects task success and learning outcomes. Existing approaches often rely on predefined behavioral categories or derive patterns without establishing their relationship to outcomes. In this work, we propose Principal Trait Analysis (PTA), a data-driven method for identifying interpretable behavioral traits from human-AI collaboration dialogues. Our method analyzes large corpora of human-AI collaborative session traces, derive common traits across the dataset, scores each human collaborator on how well their interaction aligns with these traits, and selects a set that covers the most variance across users. While unsupervised and data-driven, our method also enables domain expertise to be injected during trait identification. We evaluate PTA on two human-AI collaborative coding datasets and investigate how the traits predict future task success, learning outcomes, and evolve over time.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05804

Matching the Training-Time Weight Rule in Inference-Time Expert Deactivation

Hao Cheng, Zhiyu Yang, Bo Ma, Hanzhang Jia

原文摘要

Expert deactivation at inference time changes both token routing and expert weights, and its effect on performance depends on how these changes are implemented. We compare removal, freezing, remaining-expert renormalization, and unnormalized re-routing on identical disabled sets across five instruction-tuned checkpoints from four model families, with a base OLMoE checkpoint as an additional comparison. We develop a weight-sum model that relates the loss of expert contributions and changes in branch scale to the weight rule used during training. With half of the experts deactivated according to activation-based rankings, remaining-expert renormalization yields the highest perplexity in models trained with raw router probabilities, whereas unnormalized re-routing yields the highest perplexity in models trained with normalized weights. Perplexity ranges from 1.4 to 73 times the intact baseline when the training rule is retained, and from 14 to 28,740 times the baseline under a rule mismatch. Task outcomes vary across evaluation types: on OLMoE, GSM8K strict-match accuracy falls to zero under all four implementations. Extending the model to changes in the number of active experts yields a further prediction, supported by the OLMoE experiments: the perplexity penalty from additional renormalization increases as fewer experts are activated.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05803

Phonological Knowledge of Chinese Characters in Language Models

Xiaozhe Ji, Renfen Hu, Hai Hu

原文摘要

How much phonological knowledge do language models (LMs) possess about Chinese characters, and how is this knowledge represented and used? We introduce PinyinBench, a controlled benchmark covering homophones, phonological features (initials, finals, and tones), and polyphonic characters. We investigate 17 text-only and multimodal LMs through three complementary approaches: behavioral evaluation, layer-wise probing, and activation steering. Behaviorally, models demonstrate substantial knowledge of initials and finals, with a frontier model (DS-v4-flash) scoring 90%+ in homophone judgment, when two characters share no phonological features. However, its accuracy drops sharply to 72% when two characters differ only in lexical tone. Probing reveals that tone is highly decodable from embeddings and improves modestly across layers, whereas segmental information starts less decodable and improves substantially with depth. Activation steering shows that segmental representations can systematically influence generation, while tone exhibits much weaker effects. Furthermore, audio-bearing training improves phonological decodability, including tone, without corresponding improvements in steering effectiveness. Together, these findings reveal distinct representational and functional profiles for segmental and tonal information, with tonal information much harder to access and manipulate, demonstrating the necessity for combined evaluation, probing, and causal intervention for understanding linguistic knowledge in LMs.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.18489

EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models

Minsoo Cheong, Donghyun Son, Woosang Lim, Sungjoo Yoo

原文摘要

Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing approximate KV caching methods reduce this cost by selectively updating cached states, but their decision overhead scales with context length or model depth. We propose EntropyCache, a training-free KV caching method that uses the maximum entropy of newly decoded token distributions as a constant-cost signal for deciding when to recompute. Our design is grounded in two empirical observations: (1) decoded token entropy correlates with KV cache drift, providing a cheap proxy for cache staleness, and (2) feature volatility of decoded tokens persists for multiple steps after unmasking, motivating recomputation of the $k$ most recently decoded tokens. The skip-or-recompute decision requires only $O(V)$ computation per step, independent of context length and model scale. Experiments on LLaDA-8B-Instruct and Dream-7B-Instruct show that EntropyCache achieves $15.2\times$-$26.4\times$ speedup on standard benchmarks and $22.4\times$-$24.1\times$ on chain-of-thought benchmarks, with competitive accuracy and decision overhead accounting for only $0.5\%$ of inference time. Code is available at https://github.com/mscheong01/EntropyCache.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.22454

Where Prefill Expert Reduction Hurts MoE Models: A Few Prompt Tokens Carry Most of the Short-Answer F1 Loss

Zhiyuan Wang, Han Wang, Shuo Zhang

原文摘要

Running prompt tokens through fewer routed experts during prefill makes mixture-of-experts (MoE) serving cheaper, but what it damages has not been measured. We locate the damage with token-, layer- and attention-path interventions in four MoE families on short-answer question answering. At half the experts the F1 loss is mostly answer form: the model still finds the answer but no longer answers briefly. The loss is made at a few tokens: the two chat-template tokens before the answer in Qwen3-30B-A3B, and the first 8-32 tokens, where the instruction sits, in DeepSeek-V2-Lite. Keeping them at full experts removes most of the F1 loss and about half and a fifth of the increase in answer NLL. Reduction changes the first-token sink statistics by less than 4%, and restoring super experts or massive activations recovers at most a quarter of the loss. We then test placement on real prompts with about 4% of tokens at full experts. Putting them on the task interface keeps F1 within one point of the unmodified model, while the same budget scattered in the documents is about 3 points worse in both prespecified primary tests of this comparison. Time to first token falls about 14% on 11K-token prompts.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05771

How Well Can Large Language Models Impersonate Individual Authors? A Comparative Evaluation

Harshit Gupta, Shunichi Ishihara

原文摘要

This study investigates the authorship impersonation capacity of six widely used large language models (LLMs): Gemini 3 Pro, Claude Opus, GPT 5.2, GPT 5.2 Pro, DeepSeek 3.2, and Grok 4.1 Fast. The evaluation was conducted using short product review texts selected to ensure high within author consistency in individual writing style. Two types of in context prompt were designed: a simple prompt with minimal instruction and a complex prompt incorporating explicit stylometric guidance for mimicry. Authorship mimicry was evaluated using a cosine distance based distance to training metric, supplemented by visual analyses of embedding distributions. The results indicate that authorship impersonation remained challenging for most LLMs, with Gemini 3 Pro showing the strongest apparent mimicry performance. However, subsequent overlap analysis revealed that Gemini 3 Pro extensively copied and reused sentences and phrases from the training texts, at levels far exceeding those observed among human authors. Follow up factor analyses showed that training set consistency was the most robust predictor of mimicry success across models, whereas author distinctiveness did not generalise as a reliable predictor. Global embedding visualisations further revealed a consistent macro level pattern: for most models, generated texts occupied regions of the embedding space that were largely separated from the corresponding human training clusters. This indicates limited convergence towards target author style and suggests the presence of model specific lexical and phraseological preferences. The findings highlight the importance of distinguishing genuine stylistic imitation from direct textual reuse and have implications for the forensic analysis of textual evidence involving potential LLM enabled impersonation.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
首次观测 · 记录 #1软件学报:jos:7712软件学报

语义迁移：面向云端大语言模型交互的数据隐私保护方法

语义迁移: 面向云端大语言模型交互的数据隐私保护方法

陈董, 欧阳朋朋, 杨彤, 刘起东, 李亚飞, 谢立伟, 丁少杰, 徐明亮

AI 速读 基于摘要

提出STPP方法，通过语义加密把隐私关键信息迁移到相似逻辑的新场景、再语义解密还原反馈，在保护云端大语言模型交互隐私的同时维持数据效用。

cs.* · cs.CL

软件学报 · 2026 · 正式发表

软件学报 ↗PDF ↗
查看原文摘要

具有强大理解、生成能力的云端大语言模型(cloud large language model, CLLM)已经成为人们日常工作中不可缺少的工具. 然而, CLLM的运行方式意味着用户需要上传原始数据, 这将使得用户的数据隐私安全难以得到有效保障. 现有数据加密方法往往通过添加噪声来改变原始数据形式, 这极易导致数据效用下降, 并影响任务效果. 不同于对原始数据的全盘保护, 将用户数据分为可被识别并用于对齐归属个体的隐私关键信息, 以及不涉及归属问题的普通信息, 并提出保护隐私关键信息, 传递普通信息, 从而在保护数据隐私安全的同时, 维持数据效用. 具体而言, 提出基于语义迁移的用户隐私保护(semantic transfer for privacy protection, STPP)方法. STPP首先基于LLM广泛的先验知识构建语义映射库与语义映射模型, 并通过语义加密将原始信息迁移到具有相似逻辑的新场景. 在获得CLLM反馈后, STPP又通过语义解密将反馈信息还原回原始场景, 从而保护用户数据隐私安全的同时, 降低所提方法对用户使用CLLM体验的影响.

新论文 · v1arXiv:2611.05759

PAYWORTHY: Can LLMs Predict Which Freelance Jobs an AI Agent Will Complete?

Mohammad Reza Rezaei, Dingxian Wang, Brett Levert, Celeste Fejzo, Andrew Rabinovich, Zhao Chen

原文摘要

Before an AI agent takes on a paid job, someone has to judge whether it is likely to succeed. We test whether frontier language models can make this call before any attempt. We propose PAYWORTHY which contains 1{,}494 real freelance job postings, sampled from 18.8M postings made between 2020 and 2026 on a freelancing platform. An agent attempts each job from the posting alone in a single run, and an LLM judge acting as the client decides whether to accept the work. We ask 18 models to forecast how likely the agent is to succeed and measure how well each model's forecasts rank the accepted jobs above the rejected ones (AUC, where 0.5 is a random ranking). The answer depends on how the agent is described. Told what the agent cannot do, every model ranks the jobs well (AUC 0.66--0.86). Told instead that it is a generic agent with a browser and code execution, the same models rank the same jobs about as well as a random ordering (0.45--0.56). These results hold under judges from four other model families (Claude, GLM, Kimi and Qwen), and the informed forecasts also rank the verdicts of two human raters. Code is available at https://github.com/upwork/Payworthy

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.30356

OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL

Karl El Hajal, Mathew Magimai. -Doss

原文摘要

We propose Online Latent prediction with Invariant Views and rEconstruction (OLIVE), a self-supervised speech representation learning framework that jointly optimizes analysis and synthesis objectives. OLIVE couples masked latent prediction and waveform reconstruction through a functional separation within a single encoder: reconstruction constrains early encoder features to retain signal-level information, while masked latent prediction shapes later contextual representations for robust downstream performance, with waveform view augmentations defining the invariances they learn. To the best of our knowledge, OLIVE is the first speech SSL model that directly reconstructs waveforms, retains its vocoder after pre-training, and remains competitive on discriminative tasks. Adding reconstruction largely preserves the speech recognition performance of masked latent prediction alone, while improving waveform reconstruction and speaker tasks. Adding waveform mixup and gain augmentations provides a controllable way to shift the representations further toward speaker, generation, and reconstruction tasks, while remaining competitive on recognition and semantic tasks.

cs.CL · cs.LG · cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05744

Text-Only Domain Adaptation for Low-Resource Medical ASR: Shallow Fusion and Density Ratio Rescoring for Hausa

Oche David Ankeli, Hassan Adelani Luqman, Theodora Ngozi Egbunike, Joshua Gottschalk, Bonaventure F. P. Dossou

原文摘要

Automatic speech recognition (ASR) systems often struggle with specialised medical vocabulary, especially in low-resource languages where domain-specific speech data are scarce. We investigate text-only domain adaptation for Hausa medical ASR using the fixed MMS-1B-FL102 acoustic model and two decoding-time language-model fusion methods: Shallow Fusion (SF) and the Density Ratio Approach (DRA). A 4-gram KenLM trained on 19,421 Hausa health sentences serves as the medical target model, while a 75,372-sentence general-domain model provides the source prior for DRA. Evaluation uses 250 recordings of 25 physician-reviewed prompts from 10 speakers across six northern Nigerian states. Under prompt-disjoint five-fold cross-validation, SF and DRA reduce WER from 29.56% to 23.55% and 23.33%, respectively. Both significantly outperform greedy decoding (p < 0.001), while their difference is not significant (p = 0.423). However, general-LM-only SF achieves 23.96% WER, indicating that the medical LM's additional improvement over a general LM is modest. Medical Term Error Rate also improves under fusion, but does not establish a distinct medical-domain advantage. These findings demonstrate that lightweight, text-only language-model fusion can improve Hausa medical ASR without additional domain-specific speech collection.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2009.03996

Combining Determinism and Indeterminism

Michael Stephen Fiske

原文摘要

Our goal is to construct mathematical operations that combine indeterminism measured from quantum randomness with computational determinism so that non-mechanistic behavior is preserved in the computation. Formally, some results about operations applied to computably enumerable (c.e.) and bi-immune sets are proven here, where the objective is for the operations to preserve bi-immunity. While developing rearrangement operations on the natural numbers, we discovered that the bi-immune rearrangements generate an uncountable subgroup of the infinite symmetric group (Sym$(\mathbb{N})$) on the natural numbers $\mathbb{N}$. This new uncountable subgroup is called the bi-immune symmetric group. We show that the bi-immune symmetric group contains the finitary symmetric group on the natural numbers, and consequently is highly transitive. Furthermore, the bi-immune symmetric group is dense in Sym$(\mathbb{N})$ with respect to the pointwise convergence topology. The complete structure of the bi-immune symmetric group and its subgroups generated by one or more bi-immune rearrangements is unknown.

math.LO · cs.CC · cs.CL · math.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05731

Prospective Memory for Proactive LLM Agents

Yuanchen Bei, Zhining Liu, Tianxin Wei, Weizhi Zhang, Zhichen Zeng, Philip S. Yu, Hendrik Hamann, Jingrui He 等 9 位作者

原文摘要

Most memory systems for LLM agents are retrospective, preserving and retrieving past information to inform current decisions. Proactive agents, however, also require prospective memory: retaining future-directed intentions and realizing them when appropriate opportunities arise, even without explicit requests. Crucially, remembering the right intention does not guarantee acting at the right time: a related observation may call for waiting, while a later cue may make the same intention actionable. Inspired by cognitive theories of human prospective memory, we introduce Pro-Memory, a memory framework that separates maintaining future intentions from deciding when and how to realize them. Pro-Memory preserves pending objectives linked to their supporting evidence, assesses new observations against their original goals and activation conditions, and coordinates appropriate contributions with the agent's ongoing actions. It further updates intention states based on actions actually issued or evidence of resolution, while an experience memory distills feedback from completed episodes into guidance for future decisions. Experiments on two benchmarks spanning delayed-intention tasks and open-ended proactive assistance demonstrate consistent improvements in proactive task performance over representative memory approaches across multiple LLM backbones, while limiting unnecessary interventions.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05720

Cognitive Bias Signatures in Search-Equipped LLM Agents: A Stage-Resolved Analysis

Yanru Xiao, Yingwei Yu

原文摘要

Search can help LLM agents correct mistakes, but their starting conditions may shape which evidence they find and use. Drawing on cognitive-bias paradigms, we develop a controlled search harness to examine result order, records of prior work, and initial hypotheses while holding each question and document collection fixed. Matched controls distinguish order effects from differences in document composition and the effects of failed work from context length. Across 10 models and 1,000 synthetic search worlds, we track queries, retrieved documents, document openings, and final answers. Our comparisons suggest that final answers are more sensitive to initial evidence order during active search than when all evidence is supplied in full. Dead-end histories can reduce strategy switching relative to matched neutral histories, indicating an effect beyond context length. Under wrong hypotheses, stage measurements distinguish reduced retrieval or opening from errors that persist after counter-evidence is opened. Exploratory interventions show that opening counter-evidence more often can coincide with lower accuracy, while accuracy can improve with little change in opening.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06956

Octopus: One Brain, Many Branches for Latent-KV Multi-Agent Reinforcement Learning

Tianming Sha

原文摘要

Multi-agent LLM systems explore in parallel by spawning sub-agents with isolated context windows, whereas single-agent systems append every search and verification step into one growing trajectory. However, existing multi-agent frameworks duplicate prefix KV caches across branches, exchange findings by re-prefilling text summaries, and flatten or drop cross-branch dependencies during reinforcement learning (RL). We introduce Octopus, a single-model multi-agent RL framework in which all threads share one backbone and coordinate over a GPU-resident directed acyclic graph (DAG) of KV states through five primitives (fork, read_thread, wait_threads, rewind, commit). Octopus combines three co-designed mechanisms: (1) Zero-Copy Radix Forking, which spawns branches as $\mathcal{O}(1)$ cursor views over shared physical KV pages; (2) Attention-Only KV Mounting, which mounts a sibling thread's terminal KV blocks directly into full-attention layers while bypassing linear-recurrent states (Gated DeltaNet / Mamba-2), cutting off-task hijacking by $21\times$ ($57.9\% \to 2.7\%$) while retaining $92.2\%$ of full-text mutual information at zero extra KV allocation; and (3) a Packed DAG-GRPO Trainer, which packs all episode branches into one block-sparse attention pass and assigns counterfactual branch credit via leave-one-branch-out marginal rewards. Trained end-to-end with GRPO on Qwen3.5-4B over a sparse BM25 corpus, Octopus reaches $49.6\%$ accuracy on BrowseComp-Plus ($+17.5$ points over single-agent GRPO at 143K context and $+12.5$ points over text-summary multi-agent RL) and $51.2\%$ on OpenResearcher, outperforming dense-retrieval agents up to $250\times$ larger while increasing training throughput $3.3\times$ and cutting peak KV memory $2.8\times$.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.18008

TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots

Fangrui Huang, Souhad Chbeir, Arpandeep Khatua, Sheng Wang, Sijun Tan, Kenan Ye, Lily Bailey, Merryn Daniel 等 11 位作者

原文摘要

Large language models (LLMs) are increasingly used for mental-health support; yet prevailing evaluation methods--fluency metrics, preference tests, and generic dialogue benchmarks--fail to capture the clinically critical dimensions of psychotherapy. We introduce THERAPYGYM, a framework that evaluates and improves therapy chatbots along two clinical pillars: fidelity and safety. Fidelity is measured using the Cognitive Therapy Rating Scale (CTRS), implemented as an automated pipeline that scores adherence to CBT techniques over multi-turn sessions. Safety is assessed using a multi-label annotation scheme, covering therapy-specific risks (e.g., failing to address harm or abuse). To mitigate bias and unreliability in LLM-based judges, we further release THERAPYJUDGEBENCH, a validation set of 116 dialogues with 1,270 expert ratings for auditing and calibration against licensed clinicians. THERAPYGYM also serves as a training harness: CTRS and safety-based rewards drive RL with configurable patient simulations spanning diverse symptom profiles. Models trained in THERAPYGYM improve on expert ratings, with average CTRS rising from 0.10 to 0.60 (and 0.16 to 0.59 under LLM judges). Our work enables scalable development of therapy chatbots that are faithful to evidence-based practice and safer in high-stakes use.

cs.CL · cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2605.14381

NodeSyn: Socially Aligned Synthetic Data for AI Evaluation

Qazi Mamunur Rashid, Xuan Yang, Zhengzhe Yang, Yanzhou Pan, Erin van Liemt, Darlene Neal, Kshitij Pancholi

原文摘要

Recent advancements in generative AI facilitate large-scale synthetic data genera- tion for model evaluation. However, without targeted approaches, these datasets often lack the sociotechnical nuance required for sensitive domains. We introduce NodeSyn, an evidence-grounded methodology that generates socially relevant syn- thetic queries by leveraging a fine-tuned taxonomy generator (TaG) anchored in real-world evidence. Evaluated against four mainstream LLMs, NodeSyn elicited failure rates up to five times higher than human-authored benchmarks. Ablation studies confirm that our granular taxonomic expansion significantly drives these failure rates, while independent validation reveals critical deficiencies in prominent guard models.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.14191

Attention to Mamba: A Recipe for Cross-Architecture Distillation

Abhinav Moudgil, Ningyuan Huang, Eeshan Gunesh Dhekane, Pau Rodríguez, Luca Zappella, Federico Danieli

原文摘要

State Space Models (SSMs) such as Mamba have become a popular alternative to Transformer models, due to their reduced memory consumption and higher throughput at generation compared to their Attention-based counterparts. On the other hand, the community has built up a considerable body of knowledge on how to train Transformers, and many pretrained Transformer models are readily available. To facilitate the adoption of SSMs while leveraging existing pretrained Transformers, we aim to identify an effective recipe to distill an Attention-based model into a Mamba-like architecture. In prior work on cross-architecture distillation, however, it has been shown that a naïve distillation procedure from Transformers to Mamba fails to preserve the original teacher performance, a limitation often overcome with hybrid solutions combining Attention and SSM blocks. The key argument from our work is that, by equipping Mamba with a principled initialization, we can recover an overall better recipe for cross-architectural distillation. To this end, we propose a principled two-stage approach: first, we distill knowledge from a traditional Transformer into a linearized version of Attention, using an adaptation of the kernel trick. Then, we distill the linearized version into an adapted Mamba model that does not use any Attention block. Overall, the distilled Mamba model retains most of the original Pythia-1B Transformer performance, reaching a perplexity of 14.01 close to the teacher's 13.86. This largely carries over to downstream tasks, although some gaps appear on tasks relying more on in-context recall. To show the efficacy of our recipe, we conduct thorough ablations at 1B scale with 10B tokens varying sequence mixer architecture, scaling analysis on model sizes and total distillation tokens, and a sensitivity analysis on tokens allocation between stages.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v7arXiv:2608.00932

Gaokerena: A Small Persian Medical Language Model Family

Mehrdad Ghassabi, Hamidreza Baradaran Kashani, Pedram Rostami, Sadra Hakim, Zahra Kazemi, Amirhossein Poursina, Milad Tavakoli, Audrina Ebrahimi

原文摘要

Persian medical natural language processing remains limited by the scarcity of domain-specific resources and insufficient public characterization of their coverage and quality. We present Gaokerena, an openly released suite of Persian medical resources comprising an 85.5-million-word corpus of 101,954 web articles; MF3QA, a 24,000-pair patient-doctor question-answering dataset; 1,878 Iranian medical examination questions (KOPP); 1,089 manually translated medical MMLU questions (FA_MED_MMLU); and approximately 18,000 machine-translated MedMCQA training items filtered by two language-model evaluators. We characterize the resources' composition, orthographic variation, redundancy, topical coverage, privacy indicators, answer-key balance, extraction artefacts, and translation limitations. As application case studies, we adapt Aya-Expanse-8B into Gaokerena-V, trained on the corpus and MF3QA, and Gaokerena-R, developed through preference-based reasoning distillation. On translated medical MMLU, Gaokerena-V achieves 49.31% accuracy under direct prompting, compared with 46.65% for Aya-Expanse-8B; the paired exact McNemar test is statistically inconclusive (p = 0.0502). Gaokerena-R reaches 52.80% using five-sample self-consistency and a verifier, but this higher-compute setting is not directly comparable. Under matched five-sample chain-of-thought self-consistency without a verifier, Gaokerena-R scores 48.58%, versus 46.92% for Aya-Expanse-8B, a non-significant difference (p = 0.190). English evaluation also reveals a substantial performance gap relative to Persian. To our knowledge, Gaokerena provides the first openly released and systematically characterized suite of Persian medical resources alongside generative models built on them. These protocol-specific results do not establish an isolated training advantage or clinical readiness.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05662

Grounded but Not Immune: Confirmation Bias in Agent-as-a-judge

Drake Benjamin Brown, Khushbu Pahwa, Yubin Ge, Salvatore Romeo, Akhil Agnihotri, Yi Zhang, Xiaofei Ma, Daniele Bonadiman

原文摘要

Evaluating open-ended agent tasks increasingly falls to an Agent-as-a-Judge: an evaluator handed tools and the agent's full trajectory so it can verify a result against the environment. The premise is that a judge that gathers its own evidence should be grounded by it. We show that this grounding does not immunize the judge against confirmation bias: a single false pre-screening note, attributed to an authority and carrying no evidential bearing on the correct verdict, overturns up to 40% of a tool-using judge's correct verdicts across four judges and five datasets, even though the judge collects decisive evidence. The shift is driven by specific properties of the cue. We treat this cue as a controlled diagnostic of confirmation bias rather than an adversarial attack. Our central contribution is to explain how confirmation bias changes the judge's behavior in a trajectory. We classify changes in judge behavior and attribute changes to one of three failure modes: over-trust (verify, conclude correctly, then defer), hallucination (fabricate support for the flip), and under-investigation (stop at the first corroborating signal). For the two Claude judges, the failure is predominantly over-trust (67-75% of harmful flips), while smaller judges have error modes spread across all three. Lightweight mitigations blunt but never remove the bias.

cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.18902

SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration

Ziyi Zhu, Luka Smyth, Saki Shinoda, Jinghong Chen

原文摘要

Context engineering has emerged as a primary lever for improving AI systems without parameter updates. Recent work showing that textual gradients do not function as real gradients motivates treating automatic prompt optimization (APO) as black-box search. We introduce SPO (Stochastic Prompt Optimization), a framework for stochastic search over prompt space, and compare three strategies of increasing sophistication: error-informed random search, a genetic algorithm with evolutionary operators, and SAGE (SPO via Agent-Guided Exploration), a multi-agent pipeline with diagnostic code execution. Across three benchmarks, no single strategy dominates; effectiveness depends on the interaction of landscape structure with error type. We further deploy SAGE on a mental-health chatbot under a continuous optimization paradigm, where it compounds eight cycles of individually-noisy A/B tests into a statistically robust gain in next-day retention. We argue that coupling qualitative diagnosis with quantitative validation is what makes agentic optimization effective for open-ended task-oriented dialogue.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2603.01865

CyclicJudge: Mitigating Judge Bias Efficiently in LLM-based Evaluation

Ziyi Zhu, Olivier Tieleman, Alexey Bukhtiyarov, Jinghong Chen

原文摘要

LLM-as-judge evaluation has become standard practice for open-ended model assessment; however, judges exhibit systematic biases that cannot be averaged out by increasing the number of scenarios or generations. These biases are often similar in magnitude to the model differences that benchmarks are designed to detect, resulting in unreliable rankings when single-judge evaluations are used. We introduce a variance decomposition that partitions benchmark score variance into scenario, generation, judge, and residual components. Based on this analysis, CyclicJudge, a round-robin assignment of judges to scenarios, is demonstrated to be the optimal strategy for a fixed judge panel and judge-call budget: it cancels the average additive judge offsets while matching the cost of single-judge evaluation. Empirical results on MT-Bench and MindEval validate the effectiveness of CyclicJudge as predicted, across both general-purpose and domain-specific evaluation settings, reducing benchmark score variance and stabilizing the resulting model ranking.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2507.10880

Domain-Adaptive Small Language Models for Structured Tax Code Prediction

Souvik Nath, Sumit Wadhwa, Luis Perez

原文摘要

Every day, multinational firms process thousands of transactions, each of which must adhere to tax regulations that vary by jurisdiction and are often nuanced. The determination of product and service tax codes, such as HSN or SAC is a major use case in Tax compliance. An accurate determination of such codes is imperative to avoid any tax penalties. This paper proposes a domain-adaptive small language model (SLM) with an encoder-decoder architecture for the enhanced prediction of product and service tax codes. In this approach, we address the problem of predicting hierarchical tax code sequences using unstructured product and services data. We employ an SLM based upon encoder-decoder architecture as this enables sequential generation of tax codes to capture the hierarchical dependencies present within the tax codes. Our experiments demonstrate that encoder-decoder SLMs can be successfully applied to the sequential prediction of structured tax codes, a domain that remains comparatively unexplored in current NLP research. In this paper, we demonstrate the superior performance of the domain-adaptive encoder-decoder SLMs over flat classifiers when applied to the Harmonized System of Nomenclature (HSN), and achieve superior results compared to decoder-only and encoder-only architectures for structured sequence generation tasks. This approach can also be scaled to other government-mandated tax commodity codes, such as United Nations Standard Products and Services Codes (UNSPSC), or Brazil's Nomenclatura Comum do Mercosul (NCM).

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2512.20773

DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation

Ziyi Zhu, Olivier Tieleman, Caitlin A. Stamatis, Luka Smyth, Thomas D. Hull, Daniel R. Cahn, Jinghong Chen, Matteo Malgaroli

原文摘要

Realistic user simulation is crucial for training and evaluating multi-turn dialogue systems, yet creating simulators that accurately replicate human behavior remains a significant challenge. An effective simulator must expose the failure modes of the systems under evaluation. This work introduces Direct Iterative Adversarial Learning (DIAL), an adversarial framework that iteratively enhances user simulator realism through a competitive dynamic between a generator (user simulator) and a discriminator. When applied to mental health support, a domain characterized by diverse failure types and a critical dependence on realistic user behavior for failure detection, DIAL restores lexical diversity diminished by supervised fine-tuning and drastically reduces discriminator accuracy. The resulting simulator exhibits a strong correlation between simulated and real failure occurrence rates while maintaining low distributional divergence of failure modes. These findings indicate that DIAL is a promising method for developing realistic user simulators in multi-turn dialogue, facilitating reliable and cost-effective system evaluation prior to deployment.

cs.CL

查看论文
arXiv ↗PDF ↗