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
+94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 01:35 — 2026-11-21 01:35(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 6,550 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:2611.25682

FoodReact-AR: Learning Audience Reactions that Zero-Shot LLMs Miss in Arabic Food-Insecurity Discourse

Wajdi Zaghouani, Mabrouka Bessghaier, Salma Azouzi, Shimaa Amer Ibrahim

原文摘要

Facebook reactions record how an audience received a post, a signal absent from the post's text. We treat the six differentiated reactions on 74,241 Arabic food-insecurity posts from public Facebook pages (2020-2024) as compositions, apply a centered log-ratio transformation, and cluster them into four audience profiles: Solidarity (Love-dominant), Dismissal (Haha-dominant), Grief (Sad-dominant), and a flat Ambivalent profile. Dismissal peaks in 2022 (22.3%), the year of the wheat price shock, and grief in 2024 (14.0%), during the Gaza food emergency; a page-clustered GEE confirms both shifts (odds ratios 2.18 and 1.34), and they survive minimum-reaction filtering, alternative zero replacements and clustering methods, and bootstrap resampling. We then test whether the profiles can be predicted without reactions. A zero-shot Arabic LLM recovers Grief for 83.8% of posts but Dismissal for only 3.4%, and in a matched ablation, it shows the reaction percentages do not help. A simple classifier trained on the reaction-derived labels and tested on unseen pages recovers dismissal for 60.0% (macro-F1 0.56 against 0.43), mainly from mentions of officials and institutions. Derisive audience responses are thus learnable from text, yet a zero-shot LLM misses them. We release the corpus, LLM, and human annotation layers, and an evaluation protocol as FoodReact-AR.

cs.CL

版本更新 · v2arXiv:2603.09185

DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval

Taegyeong Lee, Jiwon Park, Seunghyun Hwang, JooYoung Jang

原文摘要

Recent advances in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) have enabled diverse retrieval methods. However, existing retrieval methods often fail to accurately retrieve results for negation and exclusion queries. To address this limitation, prior approaches rely on embedding adaptation or fine-tuning, which introduce additional computational cost and deployment complexity. We propose Direct Embedding Optimization (DEO), a training-free method for negation-aware text and multimodal retrieval. DEO decomposes queries into positive and negative components and optimizes the query embedding with a contrastive objective. Without additional training data or model updates, DEO outperforms baselines on NegConstraint, with gains of +0.0738 nDCG@10 and +0.1028 MAP@100, while improving Recall@5 by +6\% over OpenAI CLIP in multimodal retrieval. These results demonstrate the practicality of DEO for negation- and exclusion-aware retrieval in real-world settings.

cs.CL

新论文 · v1arXiv:2611.25672

SEAF: Selective Semantic Enrichment and Visual Evidence Fusion for Multimodal Sarcasm Detection

Faxian Wan, Xiaocui Yang, Yifan Cao, Shi Feng, Daling Wang, Yifei Zhang

原文摘要

Multimodal sarcasm detection requires textual, visual, and contextual evidence, particularly when multiple images provide complementary cues. Multimodal large language models (MLLMs) can generate auxiliary information from a post's text and images, but their outputs may mix useful background knowledge with redundant visual descriptions. We propose SEAF, a dual-branch framework for selective semantic enrichment and visual evidence fusion. SEAF assigns generated fields to distinct roles: entity background enriches semantic input, while image descriptions supply alignment statistics. The semantic branch combines the original post text, background from a frozen MLLM, and optical character recognition (OCR) text. The aligned visual branch combines global and local visual features with statistics of cross-modal and inter-image similarity. Text-Anchored Smoothed Aggregation (TASA) weights images by their similarity to the original post text while preserving contributions from images with low literal similarity. Summing the branch classification scores integrates contextual semantics with visual evidence. Experiments on the multi-image MMSD3.0 benchmark show that SEAF outperforms all compared methods.

cs.CV · cs.CL

版本更新 · v2arXiv:2611.20846

EDITORS Know Your Style! Editing LoRA Subspaces for Stylistic Attribution and Imitation

Zixuan Wang, Gregory Kang Ruey Lau, Xiao Tian, Jue Fan, Caroline Chaux, Bryan Kian Hsiang Low

原文摘要

Disentangling writing style from semantic content is a fundamental challenge in literary text modeling. Style-content entanglement causes models to rely on semantic content for authorship attribution (AA) tasks and memorize author-specific content for style imitation (SI) tasks. We propose EDITORS (EditingLoRA Subspaces), a diagnose-then-deflate framework that adapts pretrained large language models and prioritizes stylistic features, making it effective for both AA and SI tasks. EDITORS first trains a diagnostic LoRA adapter using style-neutral statements derived from the training corpus to identify a content-oriented subspace. It then trains the final style adapter under activation-space deflation that projects input activations away from the identified content-oriented directions. We empirically demonstrate that EDITORS is effective. On three AA benchmarks spanning literature, social media, and news, EDITORS achieves state-of-the-art accuracy, outperforming the strongest existing baseline by up to 29%. On SI, EDITORS generates stylistically faithful and diverse passages, outperforming baselines in achieving style similarity while adhering to content specifications.

cs.CL · cs.AI

新论文 · v1arXiv:2611.25653

ColorRef: Calibrating Verbal Feedback for Color Revision

Pablo Loyola, Andres Hoyos-Idrobo, Edison Marrese-Taylor, Colin Rowat, Alfredo Solano

原文摘要

People rarely specify an exact color when asking someone to revise a design: they might say \textit{a little darker} or \textit{more blue} after seeing a proposal. A language-model assistant must then infer not only which way to change the color, but how far. We study this distinction with \textsc{ColorRef}, a color reference game in which a model guesses a color from a description and a teacher, knowing a recorded target hidden from the guesser, supplies verbal corrections. On 1{,}000 crowd-sourced description--target pairs, three rounds of deterministic oracle feedback reduce mean target distance from 42.33 to 22.15 $ΔE_{76}$. However, those corrections provide additional information, and improvement alone does not establish well-calibrated feedback following. A controlled Qwen3-14B diagnostic reveals a more specific failure: following a requested direction and ordering graded phrases do not guarantee a suitable step size; strong modifiers can induce excessive changes. We therefore measure each receiver's typical response to \textit{a little}, \textit{somewhat}, and \textit{much} on separate colors and select wording matched to its observed steps. On 128 held-out starting colors, calibration reduces one-step mean error from 12.36 to 6.86 for Qwen3-14B and from 11.06 to 5.89 for Gemma 4 12B against a fixed graded-wording rule. The benefit is concentrated on large corrections, with many unchanged cases and no consistent increase in threshold success. Our findings show that following the direction of feedback is not the same as making an appropriately sized revision.

cs.CL

新论文 · v1arXiv:2611.25643

TRAC: Efficient Diffusion Language Models for Machine Translation via Length-Aware Decoding

Tianyuan Li, Xihan Yang, Chenglong Wang, Yuzhang Wu, Jingbo Zhu, Tong Xiao

原文摘要

Machine translation with large language models requires both high translation quality and low generation latency. Accelerating translation while preserving quality is therefore essential for practical deployment. Diffusion large language models (dLLMs) can generate tokens at arbitrary target positions through iterative denoising, offering a new paradigm for parallel translation beyond sequential autoregressive decoding. However, existing methods still incur redundant computation: fixed target generation lengths waste computation on unused positions, while confidence-only commitment delays medium-confidence tokens whose predictions have largely stabilized. To address these issues, we propose TRAC, a training-free adaptive decoding method for diffusion machine translation. TRAC adapts the target generation length using source length and translation direction, with a conservative fallback to the maximum length for empty or unusually short outputs. It preserves high-confidence commitment while identifying temporally stable medium-confidence tokens for early commitment using cross-step top-1 persistence and approximate Jensen-Shannon divergence over Top-$K$ distributions. On bidirectional Chinese-English translation across FLORES-200, WMT23, and NTREX-128, TRAC reduces model forward calls by 24.9% to 36.8% and achieves sentence-level generation speedups of 1.91 to 2.19 times over Fast-dLLM, with only a 0.02-point decrease in macro-average COMET. These results demonstrate that adaptive generation lengths and stability-aware token commitment improve the efficiency of diffusion machine translation.

cs.CL

版本更新 · v2arXiv:2611.02011

MedPsy: State-of-the-Art Small Medical Language Models for Efficient Edge Deployment

Davide Vitabile, Alexandro Buffa, Akshay Nambiar, Amril Nazir

原文摘要

Medical language models promise expert clinical support, but the strongest open-source LLMs remain too large for private edge-device deployment, while compact medical models still trail substantially on knowledge-intensive and real-world healthcare tasks. Reasoning models that fit edge memory budgets can produce long reasoning traces, increasing sequential decoding, end-to-end latency, energy consumption, and KV-cache memory pressure. We present MedPsy, a family of text-only 1.7B and 4B medical language models designed for edge deployment, targeting this accuracy-generation-efficiency trade-off. Our recipe combines a synthetic medical data pipeline over biology, medicine, and health seeds with chain-of-thought targets from a 235B medical-focused LLM teacher; a four-stage post-training curriculum comprising two SFT stages followed by two RL stages with hard-sample mining; and an edge deployment evaluation spanning multiple GGUF quantization variants and real-device inference on laptop and smartphone hardware. On seven closed-ended medical benchmarks, MedPsy-4B surpasses MedGemma-1.5-4B by 19.34 points and matches MedGemma-27B while being 6.75x smaller; MedPsy-1.7B outperforms MedGemma-1.5-4B by 11.42 points despite being less than half its size. On HealthBench-Hard, MedPsy-4B surpasses MedGemma-27B by 15.33 points, while MedPsy-1.7B surpasses it by 11.66 points despite being ~16x smaller. Beyond accuracy, MedPsy reduces average response length by 1.7x (1.7B) and 3.2x (4B) versus its Qwen3 backbones, while Q4_K_M quantization preserves the aggregate score within 1 point of BF16 with ~69% lower disk footprint. In real-device inference, MedPsy-4B's shorter generations translate into 75% lower median end-to-end latency and estimated energy per answer than its Qwen3 backbone at matched quantization, while peak RAM remains below 5 GB across our tested laptop and smartphone configurations.

cs.CL

版本更新 · v6arXiv:2606.06840

Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces

Debjyoti Saha Roy

原文摘要

Reasoning-trained language models can pick a document's few labels from thousands of candidates, zero-shot. We ask which components make these choices, and whether a student can be taught where to look as well as what to write, so its decisions trace to a few components and what they read. We study clinical coding of MIMIC-IV discharge summaries with all 5,651 candidate codes in the prompt. Each choice is one token: a region of the code list, a code within it, or the departure from a similar code named earlier. We measure each attention head's causal effect there by removing it and transplanting it into another summary. On essentially every summary, a small, shared set of heads, partly specific to each kind of choice, is necessary and sufficient; blocking what the tested heads read removes their effect. MISTILL builds on this: besides the teacher's text, it supervises where the student attends at the teacher's decision tokens. In a cross-family student, its own heads, found after training, restore nearly twice as much of the choice between similar codes as before, where chain-of-thought distillation alone adds under a third; one that already carried most of it gains a little, consistently across seeds, and both gains hold on the students' own completed traces. On two corpora with coder-marked evidence, a MISTILL student's decision heads attend to it more, and more specifically, than a chain-of-thought-distilled student's. Controls locate the gain in supervising attention at the decision tokens; in the cross-family student, a target built from unselected teacher heads loses it. No task difference from chain-of-thought distillation is detected at matched precision. The structure recurs in a second reasoner; ranked heads beat random ones on legal-document labelling and code generation; and without retraining the students keep their gain on Spanish case reports and a QA benchmark.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.25606

Generative News Recommendation Reproduces Popularity: A Memorization-Based Analysis

Shotaro Ishihara

原文摘要

Text-based generative recommenders can go beyond ranking existing items by directly generating item titles or other textual representations. In the news domain, this raises a societal concern that models may repeatedly surface already popular articles and thereby narrow the diversity of information to which users are exposed. We investigate training-data memorization as one mechanism behind this concentration. Using approximately 20 million browsing sessions from a Japanese news service, we continually trained an instruction-tuned Llama 3 8B model to generate the next article title in a session. The generated-title distribution was more concentrated and less diverse than the distribution of titles observed in the browsing logs. Frequently repeated target titles exhibited greater verbatim and approximate memorization, and more strongly memorized titles were generated in response to a wider range of prompts. These findings support a pathway in which popularity in behavioral logs becomes repeated training text, is preferentially memorized, and is subsequently reproduced by a generative recommender. An exploratory target-level deduplication condition reduced both memorization and output concentration, while substantially reducing the training-set size and recommendation accuracy. Our results suggest that popularity bias in generative recommendation may arise not only from user preferences or ranking objectives, but also from the model's tendency to reproduce frequently encountered strings, with important implications for information diversity on news platforms.

cs.IR · cs.CL

新论文 · v1arXiv:2611.25588

Rubric Semantics or Numerical Priors? Auditing Scale-Direction Bias in LLM Judges

Chanwoo Kim, Doyun Kim, Minsoo Song, Sihyeon Lee, Chanjun Park

原文摘要

Recent benchmark evaluations increasingly rely on Large Language Models (LLMs) as automatic judges. This paradigm assumes LLMs evaluate based on the rubric's semantic meaning rather than its numeric scale. We question this assumption by introducing semantic faithfulness: the principle that semantically equivalent rubrics must yield consistent scores. To quantify this, we propose a scale-reversal probe that inverts score anchors without altering evaluation criteria. Furthermore, we introduce floor normalization to calibrate reversal disagreement against intrinsic model variability, enabling fair cross-model comparisons. Experiments across five meta-evaluation benchmarks with seven diverse LLM judges spanning open-weight and proprietary models reveal widespread violations of semantic faithfulness, showing that raw reversal agreement alone is misleading. Finally, we demonstrate that bidirectional anchor averaging reduces dependence on any single anchor direction without compromising alignment with human judgments. Our findings emphasize that trustworthy LLM judges must reliably follow rubric semantics, not just correlate with human ratings.

cs.CL

新论文 · v1arXiv:2611.25582

AutoRAGBench: A Benchmark for LLM Agents Automating RAG System Development

Hang Zhang, Yuzhi Pan, Ziyao Zhong, Chaokun Wang, Shuo Cao, Zeyu Huang, Yue Xue, Fang Niu 等 15 位作者

原文摘要

Retrieval-augmented generation (RAG) is a well-established paradigm for augmenting large language models (LLMs) with information retrieved from external corpora. However, developing effective RAG systems requires substantial engineering effort and iterative experimentation, as effective design choices vary across tasks and domains. With rapid advances in LLM agent capabilities, we ask how well these agents can autonomously build RAG systems and how effectively they can improve them through iteration. In this paper, we propose AutoRAGBench, the first benchmark to evaluate how well LLM agents develop RAG systems from scratch in an open code space. It comprises nine RAG system development tasks. For each task, agents build RAG systems from scratch without starter code or prescribed strategies, under a six-hour budget on a single H800 GPU. They analyze task data, implement RAG pipelines, and iteratively refine their designs based on experimental feedback. We evaluate nine agent configurations and analyze both the effectiveness of the resulting RAG systems and their development trajectories. GPT-6.1 Sol with Codex CLI achieves the highest average score of 56.1. The composite Human-SOTA baseline averages 44.4. These results show that LLM agents can automate effective RAG system development. When starting from a human-designed system on each of seven tasks, GPT-6.1 Sol with Codex CLI improves the score by 16.6 points on average.

cs.CL · cs.AI · cs.IR

新论文 · v1arXiv:2611.25557

The Coverage Selection Gap: Ranking, Not Generation, Limits LLM Rubric Construction

Ali Karkehabadi, Jamshid Hassanpour, Rafael E. Banchs

原文摘要

Task-specific rubrics are increasingly used to evaluate open-ended language-model outputs, yet constructing comprehensive evaluation criteria from complex source documents remains challenging. We study automatic rubric construction in professional mergers and acquisitions (M&A) due diligence, where evaluation criteria must be inferred from task instructions and supporting documents without access to an expert-authored reference rubric. We introduce a multi-axis generation framework that explores complementary structural and free-form views of the source evidence to construct a broad pool of candidate evaluation criteria. To distinguish failures of criterion discovery from failures of candidate selection, we introduce the coverage-selection gap, which measures the difference between reference-free ranking and a reference-informed greedy diagnostic under a fixed selection budget. Developed on 16 tasks and evaluated on four held-out tasks, our framework achieves 0.876 macro recall against senior-authored reference rubrics under an LLM-based criterion-equivalence protocol. Ablation studies further show that introducing new structural search axes improves recall by 6-10 percentage points, whereas increasing generation volume along existing search directions yields at most 1.5 points. These findings suggest that, once a high-coverage candidate pool has been constructed, effective reference-free selection becomes a substantial bottleneck in document-grounded rubric construction.

cs.CL · cs.AI

版本更新 · v3arXiv:2609.22226

Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time

Agnibh Karmakar, Mayur Parvatikar, Shreyash Dhoot, Amit Dhanda, Aman Chadha, Kapil Wanaskar, Vinija Jain, Amitava Das

原文摘要

Decode-time alignment methods steer a frozen language model by scoring candidate continuations with an external reward and selecting the maximiser. We argue that this shared design is a single degenerate point in a much larger space. We introduce Swiss-Knife, a framework for externalised multi-objective alignment in which the alignment specification is a first-class runtime object: hot-swappable scoring blades, a batch normaliser, a pairwise aggregation operator, and a selection rule. Six axioms characterise the admissible aggregation operators, and we prove a representation theorem: every operator satisfying them has the form $R_i = \sum_{j \neq i} g((μ_i - μ_j)/s(σ_i,σ_j))$, a two-parameter family containing probit and logistic comparison rules and pointwise argmax as named coordinates. Within it, pairwise aggregation is Lipschitz-stable under adversarial reward contamination while argmax is not, and Candidate-Batch Normalization (CBN) makes the weight simplex invariant to the rescalings under which reward models are only ever identified. Our reference instantiation pairs DPO-LoRA blades with an uncertainty-aware pairwise tournament. Sweeping the helpfulness/honesty/harmlessness simplex, it attains the best balanced frontier of six decode-time methods (harmonic $F_1$ 0.797 vs. 0.750 for the strongest baseline, $p < 10^{-14}$) with the lowest refusal rate and highest helpfulness of any arm, and reconfigures its objectives in 0.05 ms with no gradient computation.

cs.CL · cs.LG · stat.ML

新论文 · v1arXiv:2611.25539

COVERAGE-TRACE: Source-Side Counterfactual Tracing for Detecting Omissions in LLM Summaries

Ali Karkehabadi, Jamshid Hassanpour, Rafael E. Banchs

原文摘要

Omissions are difficult to verify because missing information leaves no output span to inspect: a summary may be factually supported while still excluding a decision, qualification, quantity, or condition needed to preserve the source's meaning. We introduce COVERAGE-TRACE, a source-side counterfactual framework that evaluates omission as dependence on a designated atomic source fact. It replaces only the target fact with type-matched alternatives, holds the candidate summary fixed, and measures the resulting change in its teacher-forced, length-normalized likelihood. A summary covering the target should respond more strongly than one omitting it, while aggregation across multiple counterfactuals reduces sensitivity to replacement choice. We evaluate COVERAGE-TRACE on 80 matched covered--omitted QMSum pairs spanning several fact types and four open-weight models. Multi-CF achieves 0.764--0.825 AUROC, compared with 0.640 for the strongest evaluated text-only baseline. On Falcon-7B, targeted interventions achieve 0.779 AUROC, whereas shuffling counterfactual assignments reduces performance to 0.533; target deletion is effective while unrelated deletion is not. However, adjustment for meaning-preserving paraphrases reduces AUROC to 0.591--0.624. COVERAGE-TRACE therefore provides a practical, complementary signal of target-specific source--summary dependence, but not a wording-invariant semantic coverage probability. These results establish source-side intervention as a promising approach to omission detection while identifying semantic invariance as the central remaining challenge.

cs.AI · cs.CL

新论文 · v1arXiv:2611.25531

LM-based Personalized Travel Planner

Amandi Nimasha, Oshadha Wijerathne, Dushan Fernando, Nisansa de Silva, Srinath Perera

原文摘要

Effective travel planning requires handling multiple information sources, managing constraints, and tailoring recommendations to user preferences. While LLMs have introduced dynamic, context-aware decision-making, single-agent models often struggle with complex multi-step reasoning, constraint adherence, and modular execution. To overcome these limitations, we propose a hierarchical multi-agent framework where a supervising chatbot agent coordinates specialized agents for schedule validation, user query formulation, real-time data retrieval, and constraint-aware itinerary generation. By integrating LLM reasoning, external APIs, and iterative refinement mechanisms based on a deterministic, multi-dimensional scoring framework, our approach ensures adaptability, efficiency, and personalization. Evaluations on the well-known TravelPlanner benchmark demonstrate improvements in Budget Constraint planning by 10\%, wider constraints set-based planning by 25\%, and personalized planning results by 45\%. compared to the ReAct baseline. Our code is available at https://github.com/nimashaklaa/TravelPlanner_Research

cs.AI · cs.CL

新论文 · v1arXiv:2611.25526

MATE: Mobile Agent Trustworthy Execution for Safe and Efficient Mobile Control

Minsuk Jang, Hee-Seon Kim, Hui-Cheol Yu, Changick Kim

原文摘要

Mobile agents on personal smartphones can affect private data, payments, settings, and the foreground screen. We present MATE (Mobile Agent Trustworthy Execution), an execution-layer system that controls the boundary between agent action proposals and device effects without modifying the underlying model. MATE represents each UI primitive as a structured action record that combines the instruction, target app, screen context, primitive, and action fields. Runtime Guardrail (RG) maps this record to an allow, block, or user-approval decision; Predefined Task Routing (PTR) serves recurring requests through verified routes with post-execution screen checks; and a floating interface keeps execution in a compact overlay. On MobileSafetyBench, MATE raises high-risk blocking from 29.7% to 97.0% under GPT-4o. On AndroidWorld, it reduces LLM calls by up to 6x and raises recurring-use task success to 95.7%.

cs.CL · cs.AI

版本更新 · v2arXiv:2611.24650

Self-Rewarded Reinforcement Learning for Better-Structured Medical Explanations in Small Language Models

Prakhar Mishra, Bhavya Yajush Awasthi, Tanuja, Nishant

原文摘要

Small language models (SLMs) can run on commodity hardware and support privacy-preserving, on-premises clinical deployment, but their medical explanations are often short and poorly structured compared with large language models. Recent supervised approaches such as Meerkat transfer chain-of-thought reasoning into 7B-8B backbones, yet their training objective does not directly target the style or organization of the generated rationales. Building on the instruction-tuned Mistral-7B backbone, we investigate whether a lightweight reinforcement learning (RL) step can improve explanation structure without human preference labels. We apply Proximal Policy Optimization (PPO) with LoRA adaptation to 2000 Meerkat-derived medical prompts, guided by a simple self-supervised reward that favors longer, lexically diverse, and well-punctuated responses while penalizing very short ones. Training for about 170 PPO steps on a single NVIDIA A100 GPU yields a stable increase in the average reward. Quantitative and qualitative comparisons show that the RL-tuned model produces longer, more organized, multi-point explanations while preserving the underlying medical content. We discuss the promise and the limitations of self-rewarded RL for shaping the style of medical explanations.

cs.AI · cs.CL

新论文 · v1arXiv:2611.25521

DRVEXO-4B-Unified: Design and Evaluation of a Modular Speech-Vision System

Zeyuan Li

原文摘要

We present DRVEXO-4B-Unified, a modular multimodal assistant built around a 4B language backbone. A self-contained checkpoint combines text, image, and speech inputs with reference-conditioned speech output and structured interaction. A temporal residual connector adapts acoustic sequences to the language interface; explicit text boundaries support incremental speech synthesis; and three task-conditioned scoring heads rank supplied action candidates alongside generative tool calls. These interfaces connect conversation to application-defined choices while leaving action authorization to the application. The system obtains 74.22% on all 900 MMMU validation questions, exceeding the published validation scores of Gemma 3 4B IT and InternVL3.5-4B without test-time scaling. Strict prompt-level IFEval accuracy is 82.26% and MATH-500 accuracy is 89.40%, above the original Qwen3-4B non-thinking report's 81.2% and 84.8%, respectively. On NVIDIA GB10, the model achieves a speech-synthesis first-chunk latency of 390 ms. For concurrent text generation, a growth-aware admission policy completes a 128-answer batch at 594.41 output tokens/s, including filling and draining, without preemptions. We plan to release the model weights and accompanying code under Apache License 2.0, retaining applicable third-party terms.

cs.CL

版本更新 · v2arXiv:2611.23788

Geometry-bridge flow matching for blind rigid-motion correction in head cone-beam CT

Sungho Yun, Seungryong Cho

原文摘要

Rigid motion of a patient head during head cone-beam CT (CBCT) scan can degrade image quality and complicate recovery of accurate anatomical structures from the measured projections. We present a 3D flow-matching prior approach that learns the image changes induced by motion. Its geometry-bridge connects motion-corrupted and motion-free Feldkamp-Davis-Kress (FDK) reconstructed images of the same source volume through progressively reduced simulated motion. The forward projector's geometry derivative supplies analytic velocity targets along this path. A plug-and-play loop encompasses the learned image updates together with spline-based pose estimation, conjugate-gradient data consistency, and image total-variation regularization. Both the refined image volume and the FDK reconstructed image volume at the estimated poses are evaluated. On simulated 360-view scans from 30 held-out CQ500 patients with nominal per-component motion amplitudes within 10 mm / 10 degrees, the framework achieved state-of-the-art image reconstruction quality and motion accuracy in comparison with other methos such as learned autofocus and diffusion-based joint reconstruction. Mean peak signal-to-noise ratio (PSNR) reached 37.1 dB and mean detector-plane reprojection error (RPE) was 0.27 mm. With matched endpoints at the inference settings, the geometry bridge improved PSNR by 1.6 dB and reduced RPE by 33% relative to image-linear training. With 50 prior updates and coarse-to-fine motion estimation, total processing time averaged 9.1 minutes per patient on an RTX A6000.

physics.med-ph · cs.CL · cs.CV

版本更新 · v2arXiv:2606.04236

Supportive Token Revealing for Fast Diffusion Language Model Decoding

Giries Abu Ayoub, Mario Barbara, Lluís Pastor-Pérez, Tanja Bien, Aneesh Barthakur, Alaa Maalouf, Loay Mualem

原文摘要

Discrete diffusion language models can generate text efficiently by updating multiple masked positions in parallel, but this parallelism introduces a quality-latency trade-off. Aggressive decoding may commit mutually dependent tokens too early, while conservative decoding requires many denoising steps. Existing methods address this tension by deciding which tokens are safe to reveal using confidence or dependency criteria. However, avoiding unsafe commits does not necessarily make the remaining masked sequence easy to decode, since uncertain tokens may depend on masked tokens, creating a bottleneck for denoising steps. We propose AXON, a training-free module that can be added on top of existing parallel decoding strategies for diffusion language models. Rather than replacing the base decoder, AXON monitors the remaining uncertain masked tokens and intervenes only when their current state suggests that additional context is needed. It then shifts the criterion from which tokens are safest to reveal to which confident reveals would best support later denoising. AXON selects anchors, confident masked tokens that uncertain positions attend to, using attention, uncertainty, and confidence signals. Experiments on reasoning and code-generation benchmarks across multiple diffusion language models show that AXON improves the quality-latency trade-off of existing parallel decoders, often reducing the number of function evaluations while maintaining or improving accuracy.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.25489

When Should a Voice Agent Speak? End-of-Turn Detection in Turkish

Ahmet Tuğrul Bayrak, Fatma Nur Korkmaz, Mustafa Sertaç Türkel, Nur Yağmur Tuncer

原文摘要

A voice agent that waits for a fixed silence before replying either interrupts users who pause mid-utterance or responds late to users who have finished. This study examines the decision at the onset of silence, using turn ends and turn-internal pauses extracted from the Real-TurnTurk corpus of Turkish dyadic video calls. A fine-tuned Turkish TurnGPT model, a zero-shot Turkish language model and a deployed multilingual detector are compared, together with voice-activity timing and facial features, under recording-disjoint and speaker-disjoint evaluation with paired cluster bootstrap tests. On held-out recordings, the fine-tuned model separates turn ends from pauses better than both text baselines and is the best calibrated of the three. Timing features of the current speaker are similarly informative, and their combination with the fine-tuned text score gives the best timing-based results; with logistic regression, this combination also outperforms the same combination with either text baseline. In a latency simulation, adding the text score to a silence timeout shortens the mean response delay at the same interruption rate. On automatic Whisper transcripts, the fine-tuned model retains its advantage over the zero-shot model.

cs.AI · cs.CL

版本更新 · v3arXiv:2609.37351

Clause-Factored Bilateral State Grounding and Scoped Passivity for Counterfactual Open-World Deductive Reasoning

Zeyu Jia, Bo Yao, Zihao Yang

原文摘要

Open-World Assumption (OWA) deduction requires distinguishing provable facts (True), refutations (False), and unprovable statements (Unknown) across counterfactual edits and unseen domains. Sequence and latent-recurrent transformers rely on distributional shortcuts, whereas chain-of-thought language models incur high autoregressive latency. We decompose OWA deduction into a clause-factored bilateral grounder ($F$) and a deductive deliberation operator ($B$), forming $B \circ F$ in Typed Edge-Factorized Bilateral Port-Hamiltonian Deliberation (TE-BPHD). Trained solely on three-way query labels without parsers or proof-depth annotations, TE-BPHD (37.85M parameters) maps clauses into a 1,440-dimensional Belnap space and propagates support through passivity-balanced implicit Port-Hamiltonian rule diodes. Across 17,036 locked ProofWriter test queries, TE-BPHD reaches 79.17 +/- 5.48% depth-5 counterfactual consistency (+23.83 to +38.67 percentage points over Seq2Seq T5, Flan-T5, and Recurrent-Depth T5) and 94.95 +/- 1.23% out-of-distribution (OOD) accuracy across 5,270 six-domain queries (92.54 +/- 3.38% macro-mean). On a paired 120-query OOD slice, TE-BPHD attains 93.61 +/- 4.59% versus 79.17% for 3-shot Qwen3-1.7B under a 2,048-token reasoning cap (+14.44 percentage points) at 9.44 versus 14,878.4 ms/query batch-16 NVIDIA L4 throughput. Operator interventions show that symmetric single-rule passivity prevents positive two-cycle modes seen in Gain-Matched Unilateral Horn (+50.00 percentage points counterfactual consistency), whereas unit-interval Grounded Product-T-Norm Logic Tensor Networks (LTN) achieve cycle-safe OOD transfer (94.50 +/- 0.87%) without linear solves, and multi-fact ParaRules prose exposes an upstream grounding trade-off (1.33 +/- 1.76% zero-shot vs. 34.11 +/- 5.01% with five-slot optimal-transport joint grounding).

cs.LG · cs.AI · cs.CL

新论文 · v1arXiv:2611.25459

PILAPS: A Bilingual Benchmark for Evaluating Pragmatic Inference across Phenomena and Settings

Jiani Cao, Anna Korhonen, Chen Cecilia Liu

原文摘要

Recent work reports strong pragmatic performance by large language models (LLMs) in English, yet whether this performance generalises across languages and evaluation settings remains unclear. This question is increasingly important as LLMs are deployed across languages, cultures, and conversational contexts. In this paper, we first introduce PILAPS, a bilingual English/Mandarin Chinese benchmark covering eight pragmatic phenomena across purpose-written and dialogue-derived items, with both culturally adapted and independently sourced data. We then evaluate eight LLMs from four families across a range of model sizes and prompting strategies. Our results reveal substantial variation across models and pragmatic phenomena: open-source models continue to struggle particularly with humour, while cross-linguistic performance varies with model origin. Our error analysis shows that, compared with human participants, models are more prone to literal interpretations in conversational contexts. Theory-of-Mind prompting lowers the literal share of errors, whereas Chain-of-Thought prompting slightly raises it. Together, these findings demonstrate that strong pragmatic performance in one evaluation setting does not necessarily generalise across languages or conversational contexts.

cs.CL

新论文 · v1arXiv:2611.25446

PAIR-MED: Policy-reward Alternation for Iterative Refinement in Multilingual Medical Reasoning

Fan Gao, Xiaohang Xu, Lang Huang, Nan Lu, Irene Li

原文摘要

Large language models demonstrate strong medical question-answering capabilities, yet reasoning performance remains uneven across languages. Process reward models (PRMs) provide step-level feedback for improving reasoning, but a fixed PRM may become increasingly misaligned with the trajectory distribution of an evolving policy during reinforcement learning, thereby reducing the reliability of its supervision. We propose a policy--reward alternating training framework that jointly adapts a medical PRM and optimizes a multilingual reasoning policy. Following supervised initialization, the current policy generates multilingual trajectories to update the PRM, which then provides process-level rewards for the next policy update. Medical step supervision maintains the PRM's medical foundation, while process, outcome, and language-related rewards guide policy learning. We develop multilingual medical PRMs (PAIR-PRM) and reasoning models (PAIR-MED) at 8B and 9B scales across 12 languages. On the medical subsets of Global-MMLU and MMLU-ProX, our models improve average accuracy by 3.01--7.47% over their corresponding Qwen backbones. On CUREMED-BENCH, PAIR-MED-9B improves the joint language consistency and logical accuracy metric by 12.88% and 7.45% over baselines for in-domain and out-of-domain languages. Further analyses examine PRM adaptation, multilingual reasoning quality, and the contributions of individual training components.

cs.CL

新论文 · v1arXiv:2611.25433

RoCoKV: Accelerating LLM Inference Serving through Uncertainty and Redundancy Aware KV Cache Compression

Payman Behnam, Elaheh Sobhani, Saad Amin, Yahya Hassan, Daniyal Khan, Biswadeep Chakraborty, Tanish Patwa, Souvik Kundu 等 9 位作者

原文摘要

KV cache compression is critical for large reasoning models, where most of the cost comes from long generated reasoning traces rather than the input prompt. These traces often contain redundant and low-utility tokens due to looping, self-verification, and corrections. However, such tokens may still receive high attention scores, making it difficult to remove them without harming the reasoning process. We propose RoCoKV, a KV cache compression method designed for large reasoning models. RoCoKV introduces two key components. First, uncertainty-guided adaptive pruning adjusts the compression strength based on the model's confidence, allocating more memory during uncertain phases and applying stronger pruning when the model is confident. Second, redundancy-aware token selection reduces the impact of tokens that are highly similar to recent reasoning content, encouraging the model to retain more informative and diverse tokens. Beyond the algorithm, we co-design RoCoKV with the serving stack: we develop fused three-phase CUDA decode kernels and integrate them into vLLM as a drop-in plugin that preserves its paged KV layout and CUDA graph capture, turning algorithmic savings into real end-to-end speedups. Extensive experiments across three reasoning benchmarks and two reasoning models demonstrate that RoCoKV consistently improves reasoning accuracy under constrained KV cache budgets, achieving higher accuracy compared to state-of-the-art KV cache compression methods. For DeepSeek-R1-Distill-Llama-8B in vLLM, RoCoKV achieves a 1.27X speedup and 38% higher throughput on AIME25, the most challenging evaluated reasoning benchmark, and a 1.43X speedup and 45% higher throughput on the long synthetic benchmark, compared with Full-KV.

cs.CL

新论文 · v1arXiv:2611.25429

Evolve Where It Matters: Coverage-Guided Self-Evolution of Agent Skills

Boyin Tan, Jiadong Zhang, Xiaosong Ma, Chun Jason Xue, Xiaowei Huang, Youcheng Sun

原文摘要

Agent skills package procedural knowledge as natural-language instructions, and a skill helps only when its instructions are correct and properly followed by the agent. Self-evolving agents revise their own skills from the runs they make, but existing methods judge each run as a whole, by its outcome or by where it went wrong, and cannot tell whether a failure comes from a wrong instruction or from one the agent did not follow. Instruction-level coverage was introduced to test skills and labels each instruction of a run as follow, not-follow, or not covered, which separates these causes. We leverage it for skill self-evolution with SkillPlumber, a framework in which an agent evolves its own skills where coverage shows they fall short. A persistent root cause analysis agent turns each label into a revision question and checks each revision against the next run, while a maintainer distills investigations across tasks into a shared strategy library. Across three benchmarks and three executors, SkillPlumber solves 64.7% to 70.5% of the tasks, 25.6 to 30.4 percentage points higher than the initial skill and 8.7 to 14.0 percentage points higher than the strongest baseline, and removing coverage reduces recovered failures by 20.8% on SkillsBench with GPT-5.5.

cs.CL · cs.AI

新论文 · v1arXiv:2611.25407

ChronoDossier: Long-Form Personas as Temporal Memory Representations

Noah Sturgill, Jinho D. Choi

原文摘要

Long-horizon agents rely on stored records to recover a person's state as facts change. Reliable answers depend on how facts are recorded, retrieved, and presented to the reader. We treat a long-form persona dossier as a memory representation of a known latent state, an invariant identity plus a timeline of facts, routines, and decision rules tied to life phases. We present ChronoDossier, a benchmark of 311 synthetic dossiers of 1k-10k words written by seven generators from dated timelines. Intrinsic metrics evaluate the records against their intended states; extrinsic metrics test recovery by five readers on a seeded 32-persona GPT-5.1 panel balanced across lengths (520 rated turns per condition). The linked states, records, evidence packets, and answers support tests of construction and evidence delivery. In a contextual-stress control, tag-scoped writer inputs remove detected out-of-scope anchor copying. Frozen questions authored on staged dossiers transfer less reliably to one-pass dossiers of the same states. In matched evidence controls, whole sections repair 29 of 32 GPT-5.1 and 25 of 30 Sonnet 4.6 failures labeled as packaging, compared with 2 of 8 and 1 of 8 answer-formation failures. Attribution uses separate key-based and key-free support measures, with model disagreements retained. Length remains confounded with persona and question composition; the observed between-bucket widening depends on excerpt construction. The benchmark supports offline evaluation against known facts. Memory acquisition from interaction and validation against real users remain outside its scope.

cs.CL

版本更新 · v4arXiv:2604.15490

Think Multilingual, Not Harder: A Framework for Analyzing and Teaching Code-Switched Reasoning

Eleanor M. Lin, David Jurgens

原文摘要

Reasoning capabilities have enabled large language models to solve increasingly complex tasks. Interestingly, while reasoning models are often trained to generate monolingual text, these models have also been observed to code-switch (i.e., mix languages). Prior works have either viewed code-switching as an undesirable error, attempted to control code-switching through modifications to input prompts or the output decoding process, or focus on narrow subsets of languages, domains, tasks, and models. We address these gaps by introducing the first linguistically and behaviorally motivated fine-tuning framework for identifying beneficial code-switched reasoning behaviors in large language models and teaching these models to code-switch more effectively for reasoning. First, we create the Code-Switched Reasoning (CoRe) corpus, consisting of 7k reasoning traces from 15 models, 18 languages, 10 scripts, and diverse reasoning domains, providing insights into potentially helpful code-switching behaviors. Then, we expand CoRe into the Extended Code-Switched Reasoning corpus (EnCoRe) with 40 carefully curated datasets for training and evaluating six interventions on code-switching in reasoning across three models and seven languages, totaling 120 fine-tuning conditions. Across 80k+ reasoning traces from both language/culture-agnostic and -specific evaluations, English-dominated reasoning, semantically accurate code-switching, and a more even mix of languages are positively associated with correct answers, whereas dense switching is associated with incorrect answers. Moreover, we are able to elicit positive behaviors through fine-tuning tasks that do not directly demonstrate code-switching. Our work suggests that small but well-curated datasets can change how reasoning models code-switch, allowing us to reap the benefits of reasoning in the many languages that lack large-scale reasoning data.

cs.CL

新论文 · v1arXiv:2611.25361

Incorporating argumentation frameworks for LLM decision-making: Task-specific design and evaluation

Bochen Han, Anshu Xiong, Mingyang Ma

原文摘要

Argumentation frameworks (AFs) provide explicit, formal mechanisms for representing and resolving conflicts and thus have been incorporated into large language model (LLM) decision-making. The benefits vary and depend on how arguments and their relations are constructed, evaluated, and incorporated into the decision process. {We abstract a workflow consisting of four stages based on existing argumentation-augmented methods} and investigate their design choices over tasks of debate-based decision-making and retrieval-based fact verification. Our evaluation with recent LLMs shows that existing methods do not consistently improve performance across the considered tasks. Motivated by this observation, we develop two task-specific methods. The first is called Qnt-Arg, which organizes arguments around the original speakers in debate materials and aggregates model-estimated argument strengths and candidate-answer priors under gradual semantics. The second is Qlt-Arg that uses credibility estimates to establish preferences between conflicting evidence items and applies grounded semantics to select acceptable evidence for subsequent LLM inference. We examine the roles of generative and decision models within the two methods. In the debate setting, Qnt-Arg consistently outperforms other argumentation-augmented methods across matched configurations; Qlt-Arg improves retrieval-based fact-verification performance compared with the baselines. These findings demonstrate the value of combining formal argumentation and LLM while highlighting the importance of aligning with tasks in argumentation construction, model selection, and the role of formal semantic reasoning.

cs.CL · cs.AI

新论文 · v1arXiv:2611.25357

Pro$^2$ Agent: Scientific Problem Probing for Autonomous AI R&D

Yixiong Chen, Liqian Peng, Tian Tan, Ziqian Lin, Blake Jianhang Chen, Chao Zhao, Yaojie Liu, Alec Go 等 9 位作者

原文摘要

Large language model (LLM) agents can now autonomously conduct AI research by writing code and running experiments. They typically do so by iteratively optimizing a codebase, while ignoring the problem structure behind the task. This formulation is effective on simpler tasks, but on difficult problems it often gets stuck in the wrong solution region because the agent never explicitly represents its understanding of the problem. We introduce Pro$^2$ Agent, which shifts the primary state of autonomous AI research from a codebase state to a Problem State: an explicit structure of what problems prevent success and which solutions are likely to address them. Pro$^2$ Agent initializes the Problem State through comprehensive analysis of available resources and constraints. It then performs targeted research to relate the identified problems to candidate solutions. Through controlled hypothesis testing, the agent updates the importance of a suspected problem or the benefit brought by a candidate solution. On the complete MLE-Bench, Pro$^2$ Agent matches the best reported medal rate (70.7%) under the standard 24-hour budget and reaches 76.0% with a 48-hour budget, the highest medal rate reported on the complete benchmark. It also achieves competitive performance on PostTrainBench. In addition, it produces research notes for each task that make the research process transparent and reusable by human researchers.

cs.AI · cs.CL