Computation and Language
No One-Size-Fits-All: Building Systems For Translation to Bashkir, Kazakh, Kyrgyz, Tatar and Chuvash Using Synthetic And Original Data
Dmitry Karpov
We explore machine translation for five Turkic
language pairs: Russian-Bashkir, Russian-Kazakh, Russian-Kyrgyz, English-Tatar, English-Chuvash. Fine-tuning nllb-200-distilled-600M with LoRA on synthetic data achieved chrF++ 49.71 for Kazakh and 46.94 for Bashkir. Prompting DeepSeek-V3.2 with retrieved similar examples achieved chrF++ 39.47 for Chuvash. For Tatar, zero-shot or
retrieval-based approaches achieved chrF++ 41.6, while for Kyrgyz the zero-shot approach reached 45.6. We release the
dataset and the obtained weights.
Read the full abstract ▾
Computation and Language
Fine-Grained Activation Steering: Steering Less, Achieving More
Zijian Feng, Tianjiao Li, Zixiao Zhu et al. (+7 more)
Activation steering has emerged as a cost-effective paradigm for modifying large
language model (LLM) behaviors. Existing methods typically intervene at the block level, steering the bundled activations of selected
attention heads, feedforward networks, or residual streams. However, we reveal that block-level activations are inherently heterogeneous, entangling beneficial, irrelevant, and harmful features, thereby rendering block-level steering coarse, inefficient, and intrusive. To investigate the root cause, we decompose block activations into fine-grained atomic unit (AU)-level activations, where each AU-level activation corresponds to a single dimension of the block activation, and each AU denotes a slice of the block weight
matrix. Steering an AU-level activation is thus equivalent to steering its associated AU. Our theoretical and empirical analysis show that heterogeneity arises because different AUs or dimensions control distinct
token distributions in LLM outputs. Hence, block-level steering inevitably moves helpful and harmful
token directions together, which reduces efficiency. Restricting intervention to beneficial AUs yields more precise and effective steering. Building on this insight, we propose AUSteer, a simple and efficient method that operates at a finer granularity of the AU level. AUSteer first identifies discriminative AUs globally by computing activation momenta on contrastive samples. It then assigns adaptive steering strengths tailored to diverse inputs and selected AU activations. Comprehensive experiments on multiple LLMs and tasks show that AUSteer consistently surpasses advanced baselines while steering considerably fewer activations, demonstrating that steering less achieves more.
Read the full abstract ▾
All authors Zijian Feng, Tianjiao Li, Zixiao Zhu, Hanzhang Zhou, Junlang Qian, Li Zhang, Jia Jim Deryl Chua, Lee Onn Mak, Gee Wah Ng, Kezhi Mao
Computation and Language
History-Guided Iterative Visual Reasoning with Self-Correction
Xinglong Yang, Zhilin Peng, Zhanzhan Liu et al. (+2 more)
Self-consistency methods are the core technique for improving the
reasoning reliability of
multimodal large
language models (MLLMs). By generating multiple
reasoning results through repeated sampling and selecting the best answer via voting, they play an important role in cross-modal tasks. However, most existing self-consistency methods are limited to a fixed “repeated sampling and voting” paradigm and do not reuse historical
reasoning information. As a result, models struggle to actively correct visual understanding errors and dynamically adjust their
reasoning during iteration. Inspired by the human
reasoning behavior of repeated verification and dynamic error correction, we propose the H-GIVR framework. During iterative
reasoning, the MLLM observes the image multiple times and uses previously generated answers as references for subsequent steps, enabling dynamic correction of errors and improving answer accuracy. We conduct comprehensive experiments on five
datasets and three models. The results show that the H-GIVR framework can significantly improve cross-modal
reasoning accuracy while maintaining low computational cost. For instance, using Llama3.2-
vision:11b on the ScienceQA
dataset, the model requires an average of 2.57 responses per question to achieve an accuracy of 78.90%, representing a 107% improvement over the baseline.
Read the full abstract ▾
All authors Xinglong Yang, Zhilin Peng, Zhanzhan Liu, Haochen Shi, Sheng-Jun Huang
Computation and Language
Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models
Yu Zhang, Xinchen Li, Jialei Zhou et al. (+6 more)
Block-wise decoding effectively improves the inference speed and quality in
diffusion language models (DLMs) by combining inter-block sequential denoising and intra-block parallel unmasking. However, existing block-wise decoding methods typically partition blocks in a rigid and fixed manner, which inevitably fragments complete semantic or syntactic constituents, leading to suboptimal performance. Inspired by the
entropy reduction hypothesis (ERH), we recognize that constituent boundaries offer greater opportunities for uncertainty reduction, which motivates us to employ
entropy analysis for identifying constituent boundaries. Therefore, we propose Swordsman, an
entropy-driven adaptive block-wise decoding framework for DLMs. Swordsman adaptively partitions blocks by identifying
entropy shifts between adjacent
tokens to better align with semantic or syntactic constituent boundaries. In addition, Swordsman dynamically adjusts unmasking thresholds conditioned on the real-time unmasking status within a block, further improving both efficiency and stability. As a training-free framework, supported by KV Cache, Swordsman demonstrates state-of-the-art performance across extensive evaluations.
Read the full abstract ▾
All authors Yu Zhang, Xinchen Li, Jialei Zhou, Hongnan Ma, Zhongwei Wan, Yiwei Shi, Duoqian Miao, Qi Zhang, Longbing Cao
Computation and Language
Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
Yujie Lin, Kunquan Li, Yixuan Liao et al. (+2 more)
Large
language models (LLMs) have demonstrated impressive capabilities across a wide range of natural
language processing tasks. However, their outputs often exhibit social biases, raising
fairness concerns. Existing debiasing methods, such as fine-tuning on additional
datasets or
prompt engineering, face scalability issues or compromise user experience in multi-turn interactions. To address these challenges, we propose a framework for detecting stereotype-inducing words and attributing
neuron-level bias in LLMs, without the need for fine-tuning or
prompt modification. Our framework first identifies stereotype-inducing adjectives and nouns via comparative analysis across demographic groups. We then attribute biased behavior to specific
neurons using two attribution strategies based on integrated gradients. Finally, we mitigate bias by directly intervening on their activations at the projection layer. Experiments on three widely used LLMs demonstrate that our method effectively reduces bias while preserving overall model performance. Code is available at the github link: https://github.com/XMUDeepLIT/Bi-directional-Bias-Attribution.
Read the full abstract ▾
All authors Yujie Lin, Kunquan Li, Yixuan Liao, Xiaoxin Chen, Jinsong Su
Computation and Language
Evaluating the Presence of Sex Bias in Clinical Reasoning by Large Language Models
Isabel Tsintsiper, Sheng Wong, Beth Albert et al. (+2 more)
Large
language models (LLMs) are increasingly embedded in healthcare workflows for documentation, education, and clinical decision support. However, these systems are trained on large text corpora that encode existing biases, including sex disparities in diagnosis and treatment, raising concerns that such patterns may be reproduced or amplified. We systematically examined whether contemporary LLMs exhibit sex-specific biases in clinical
reasoning and how model configuration influences these behaviours. We conducted three experiments using 50 clinician-authored vignettes spanning 44 specialties in which sex was non-informative to the initial diagnostic pathway. Four general-purpose LLMs (ChatGPT (gpt-4o-mini), Claude 3.7 Sonnet, Gemini 2.0 Flash and DeepSeekchat). All models demonstrated significant sex-assignment skew, with predicted sex differing by model. At temperature 0.5, ChatGPT assigned female sex in 70% of cases (95% CI 0.66-0.75), DeepSeek in 61% (0.57-0.65) and Claude in 59% (0.55-0.63), whereas Gemini showed a male skew, assigning a female sex in 36% of cases (0.32-0.41). Contemporary LLMs exhibit stable, model-specific sex biases in clinical
reasoning. Permitting abstention reduces explicit labelling but does not eliminate downstream diagnostic differences. Safe clinical integration requires conservative and documented configuration, specialty-level clinical data
auditing, and continued human oversight when deploying general-purpose models in healthcare settings.
Read the full abstract ▾
All authors Isabel Tsintsiper, Sheng Wong, Beth Albert, Shaun P Brennecke, Gabriel Davis Jones
Computation and Language
Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning
Jie Deng, Hanshuang Tong, Jun Li et al. (+4 more)
Large
language models (LLMs) have made impressive strides in mathematical
reasoning, often fine-tuned using rejection sampling that retains only correct
reasoning trajectories. While effective, this paradigm treats supervision as a binary filter that systematically excludes teacher-generated errors, leaving a gap in how
reasoning failures are modeled during training. In this paper, we propose TrajFusion, a fine-tuning strategy that reframes rejection sampling as a structured supervision construction process. Specifically, TrajFusion forms fused trajectories that explicitly model trial-and-error
reasoning by interleaving selected incorrect trajectories with reflection
prompts and correct trajectories. The length of each fused sample is adaptively controlled based on the frequency and diversity of teacher errors, providing richer supervision for challenging problems while safely reducing to vanilla rejection sampling fine-tuning (RFT) when error signals are uninformative. TrajFusion requires no changes to the architecture or training objective. Extensive experiments across multiple math
benchmarks demonstrate that TrajFusion consistently outperforms RFT, particularly on challenging and long-form
reasoning problems.
Read the full abstract ▾
All authors Jie Deng, Hanshuang Tong, Jun Li, Shining Liang, Ning Wu, Hongzhi Li, Yutao Xie
Computation and Language
Can Vision Replace Text in Working Memory? Evidence from Spatial n-Back in Vision-Language Models
Sichu Liang, Hongyu Zhu, Wenwen Wang et al. (+1 more)
Working
memory is a central component of intelligent behavior, providing a dynamic workspace for maintaining and updating task-relevant information. Recent work has used n-back tasks to probe working-
memory-like behavior in large
language models, but it is unclear whether the same probe elicits comparable computations when information is carried in a visual rather than textual code in
vision-
language models. We evaluate Qwen2.5 and Qwen2.5-VL on a controlled spatial n-back task presented as matched text-rendered or image-rendered grids. Across conditions, models show reliably higher accuracy and d' with text than with
vision. To interpret these differences at the process level, we use trial-wise log-probability evidence and find that nominal 2/3-back often fails to reflect the instructed lag and instead aligns with a recency-locked comparison. We further show that grid size alters recent-repeat structure in the stimulus stream, thereby changing interference and error patterns. These results motivate computation-sensitive interpretations of
multimodal working
memory.
Read the full abstract ▾
All authors Sichu Liang, Hongyu Zhu, Wenwen Wang, Deyu Zhou
Computation and Language · Cross-listed from cs.AI
From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents
SeungWon Seo, SooBin Lim, SeongRae Noh et al. (+2 more)
Embodied agents operating in multi-
agent, partially observable, and decentralized environments must plan and act despite pervasive uncertainty about hidden objects and collaborators' intentions. Recent advances in applying Large
Language Models (LLMs) to
embodied agents have addressed many long-standing challenges, such as high-level goal decomposition and online adaptation. Yet, uncertainty is still primarily mitigated through frequent inter-
agent communication. This incurs substantial
token and time costs, and can disrupt established workflows, when human partners are involved. We introduce PCE, a Planner-Composer-Evaluator framework that converts the fragmented assumptions latent in LLM
reasoning traces into a structured decision tree. Internal nodes encode environment assumptions and leaves map to actions; each path is then scored by scenario likelihood, goal-directed gain, and execution cost to guide rational action selection without heavy communication. Across two challenging multi-
agent benchmarks (C-WAH and TDW-MAT) and three diverse LLM backbones, PCE consistently outperforms communication-centric baselines in success rate and task efficiency while showing comparable
token usage. Ablation results indicate that the performance gains obtained by scaling model capacity or
reasoning depth persist even when PCE is applied, while PCE consistently raises the baseline across both capacity and
reasoning-depth scales, confirming that structured uncertainty handling complements both forms of scaling. A user study further demonstrates that PCE produces communication patterns that human partners perceive as more efficient and trustworthy. Together, these results establish a principled route for turning latent LLM assumptions into reliable strategies for uncertainty-aware planning.
Read the full abstract ▾
All authors SeungWon Seo, SooBin Lim, SeongRae Noh, Haneul Kim, HyeongYeop Kang
Computation and Language
A Domain-Specific Curated Benchmark for Entity and Document-Level Relation Extraction
Marco Martinelli, Stefano Marchesin, Vanessa Bonato et al. (+6 more)
Information Extraction (IE), encompassing Named Entity Recognition (NER), Named Entity Linking (NEL), and Relation Extraction (RE), is critical for transforming the rapidly growing volume of scientific publications into structured, actionable knowledge. This need is especially evident in fast-evolving biomedical fields such as the gut-
brain axis, where research investigates complex interactions between the gut microbiota and
brain-related disorders. Existing biomedical IE
benchmarks, however, are often narrow in scope and rely heavily on distantly supervised or automatically generated annotations, limiting their utility for advancing robust IE methods. We introduce GutBrainIE, a
benchmark based on more than 1,600 PubMed abstracts, manually annotated by biomedical and terminological experts with fine-grained entities, concept-level links, and relations. While grounded in the gut-
brain axis, the
benchmark's rich schema, multiple tasks, and combination of highly curated and weakly supervised data make it broadly applicable to the development and evaluation of biomedical IE systems across domains.
Read the full abstract ▾
All authors Marco Martinelli, Stefano Marchesin, Vanessa Bonato, Giorgio Maria Di Nunzio, Nicola Ferro, Ornella Irrera, Laura Menotti, Federica Vezzani, Gianmaria Silvello
Computation and Language · Cross-listed from eess.AS
Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancement
Chien-Chun Wang, Hung-Shin Lee, Hsin-Min Wang et al. (+1 more)
Pre-trained models for automatic
speech recognition (ASR) and
speech enhancement (SE) have exhibited remarkable capabilities under matched noise and channel conditions. However, these models often suffer from severe performance degradation when confronted with domain shifts, particularly in the presence of unseen noise and channel distortions. In view of this, we in this paper present URSA-GAN, a unified and domain-aware generative framework specifically designed to mitigate mismatches in both noise and channel conditions. URSA-GAN leverages a dual-
embedding architecture that consists of a noise encoder and a channel encoder, each pre-trained with limited in-domain data to capture domain-relevant representations. These
embeddings condition a GAN-based
speech generator, facilitating the synthesis of
speech that is acoustically aligned with the target domain while preserving phonetic content. To enhance generalization further, we propose dynamic
stochastic perturbation, a novel regularization technique that introduces controlled variability into the
embeddings during generation, promoting robustness to unseen domains. Empirical results demonstrate that URSA-GAN effectively reduces character error rates in ASR and improves perceptual metrics in SE across diverse noisy and mismatched channel scenarios. Notably, evaluations on compound test conditions with both channel and noise degradations confirm the generalization ability of URSA-GAN, yielding relative improvements of 16.16% in ASR performance and 15.58% in SE metrics.
Read the full abstract ▾
All authors Chien-Chun Wang, Hung-Shin Lee, Hsin-Min Wang, Berlin Chen
Computation and Language
DeFrame: Debiasing Large Language Models Against Framing Effects
Kahee Lim, Soyeon Kim and Steven Euijong Whang
As large
language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial. Despite many efforts, an ongoing challenge is hidden bias: LLMs appear fair under standard evaluations, but can produce biased responses outside those evaluation settings. In this paper, we identify framing – differences in how semantically equivalent
prompts are expressed (e.g., "A is better than B" vs. "B is worse than A") – as an underexplored contributor to this gap. We first introduce the concept of "framing disparity" to quantify the impact of framing on
fairness evaluation. By augmenting
fairness evaluation
benchmarks with alternative framings, we find that (1)
fairness scores vary significantly with framing and (2) existing debiasing methods improve overall (i.e., frame-averaged)
fairness, but often fail to reduce framing-induced disparities. To address this, we propose a framing-aware debiasing method that encourages LLMs to be more consistent across framings. Experiments demonstrate that our approach reduces overall bias and improves robustness against framing disparities, enabling LLMs to produce fairer and more consistent responses.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.CV
Beyond Static Cropping: Layer-Adaptive Visual Localization and Decoding Enhancement
Zipeng Zhu, Zhanghao Hu, Qinglin Zhu et al. (+5 more)
Large
Vision-
Language Models (LVLMs) have advanced rapidly by aligning visual patches with the text
embedding space, but a fixed visual-
token budget forces images to be resized to a uniform pretraining resolution, often erasing fine-grained details and causing
hallucinations via over-reliance on
language priors. Recent
attention-guided enhancement (e.g., cropping or region-focused
attention allocation) alleviates this, yet it commonly hinges on a static "magic layer" empirically chosen on simple recognition
benchmarks and thus may not transfer to complex
reasoning tasks. In contrast to this static assumption, we propose a dynamic perspective on visual grounding. Through a layer-wise sensitivity analysis, we demonstrate that visual grounding is a dynamic process: while simple object recognition tasks rely on middle layers, complex visual search and
reasoning tasks require visual information to be reactivated at deeper layers. Based on this observation, we introduce Visual Activation by Query (VAQ), a metric that identifies the layer whose
attention map is most relevant to query-specific visual grounding by measuring
attention sensitivity to the input query. Building on VAQ, we further propose
LASER (Layer-adaptive
Attention-guided Selective visual and decoding Enhancement for
Reasoning), a training-free inference procedure that adaptively selects task-appropriate layers for visual localization and question answering. Experiments across diverse VQA
benchmarks show that
LASER significantly improves VQA accuracy across tasks with varying levels of complexity.
Read the full abstract ▾
All authors Zipeng Zhu, Zhanghao Hu, Qinglin Zhu, Yuxi Hong, Yijun Liu, Jingyong Su, Yulan He, Lin Gui
Computation and Language
Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification
Branislav Pecher, Michal Spiegel, Robert Belanec et al. (+1 more)
Large
language models (LLMs) are widely used as zero-shot and few-shot classifiers, where task behaviour is largely controlled through prompting. A growing number of works have observed that LLMs are sensitive to
prompt variations, with small changes leading to large changes in performance. However, in many cases, the investigation of sensitivity is performed using underspecified
prompts that provide minimal task instructions and weakly constrain the model's output space. In this work, we argue that a significant portion of the observed
prompt sensitivity can be attributed to
prompt underspecification. We systematically study and compare the sensitivity of underspecified
prompts and
prompts that provide specific instructions. Utilising performance analysis, logit analysis, and linear probing, we find that underspecified
prompts exhibit higher performance variance and lower logit values for relevant
tokens, while instruction-
prompts suffer less from such problems. However, linear probing analysis suggests that the effects of
prompt underspecification have only a marginal impact on the internal LLM representations, instead emerging in the final layers. Overall, our findings highlight the need for more rigour when investigating and mitigating
prompt sensitivity.
Read the full abstract ▾
All authors Branislav Pecher, Michal Spiegel, Robert Belanec, Jan Cegin
Computation and Language
How Few-shot Demonstrations Affect Prompt-based Defenses Against LLM Jailbreak Attacks
Yanshu Wang, Shuaishuai Yang, Jingjing He et al. (+1 more)
Large
Language Models (LLMs) face increasing threats from jailbreak attacks that bypass safety
alignment. While
prompt-based defenses such as Role-Oriented
Prompts (RoP) and Task-Oriented
Prompts (ToP) have shown effectiveness, the role of few-shot demonstrations in these defense strategies remains unclear. Prior work suggests that few-shot examples may compromise safety, but lacks investigation into how few-shot interacts with different system
prompt strategies. In this paper, we conduct a comprehensive evaluation on multiple mainstream LLMs across four safety
benchmarks (AdvBench, HarmBench, SG-Bench, XSTest) using six jailbreak attack methods. Our key finding reveals that few-shot demonstrations produce opposite effects on RoP and ToP: few-shot enhances RoP's safety rate by up to 4.5% through reinforcing role identity, while it degrades ToP's effectiveness by up to 21.2% through distracting
attention from task instructions. Based on these findings, we provide practical recommendations for deploying
prompt-based defenses in real-world LLM applications.
Read the full abstract ▾
All authors Yanshu Wang, Shuaishuai Yang, Jingjing He, Tong Yang
Computation and Language
Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision
Lingzhuang Sun, Ruitong Liu, Yuxia Zhu et al. (+5 more)
Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex
reasoning capabilities of
Multimodal Large
Language Models (MLLMs). However, prevailing paradigms typically rely on solitary rollout strategies where the model works alone. This lack of intermediate oversight renders the
reasoning process susceptible to error propagation, where early logical deviations cascade into irreversible failures, resulting in noisy optimization signals. In this paper, we propose the Guided Verifier framework to address these structural limitations. Moving beyond passive terminal rewards, we introduce a dynamic verifier that actively co-solves tasks alongside the policy. During the rollout phase, this verifier interacts with the policy model in real-time, detecting inconsistencies and providing directional signals to steer the model toward valid trajectories. To facilitate this, we develop a specialized data synthesis pipeline targeting
multimodal hallucinations, constructing CoRe
dataset of process-level negatives and Correct-guide
Reasoning trajectories to train the guided verifier. Extensive experiments on MathVista, MathVerse and MMMU indicate that by allocating compute to collaborative inference and dynamic verification, an 8B-parameter model can achieve strong performance.
Read the full abstract ▾
All authors Lingzhuang Sun, Ruitong Liu, Yuxia Zhu, Xiaohan Xu, Jingxuan Wei, Xiangxiang Zhang, Bihui Yu, Wentao Zhang
Computation and Language
Proxy Compression for Language Modeling
Lin Zheng, Xinyu Li, Qian Liu et al. (+2 more)
Modern
language models are trained almost exclusively on
token sequences produced by a fixed tokenizer, an external lossless compressor often over UTF-8 byte sequences, thereby coupling the model to that compressor. This work introduces proxy compression, an alternative training scheme that preserves the efficiency benefits of compressed inputs while providing an end-to-end, raw-byte interface at inference time. During training, a single
language model is jointly trained on raw byte sequences and compressed views generated by external compressors; through the process, the model learns to internally align compressed sequences and raw bytes. This
alignment enables strong transfer between the two formats, even when training predominantly on compressed inputs that are discarded at inference. Extensive experiments on code
language modeling demonstrate that proxy compression substantially improves training efficiency and significantly outperforms pure byte-level baselines given fixed compute budgets. As model scale increases, these gains become more pronounced, and proxy-trained models eventually match or surpass tokenizer approaches, all while operating solely on raw bytes and retaining the inherent robustness of byte-level modeling. Our code is available at https://github.com/LZhengisme/proxy-compression.
Read the full abstract ▾
All authors Lin Zheng, Xinyu Li, Qian Liu, Xiachong Feng, Lingpeng Kong
Computation and Language
Contextual Drag: How Errors in the Context Affect LLM Reasoning
Yun Cheng, Xingyu Zhu, Haoyu Zhao et al. (+1 more)
Central to many self-improvement pipelines for large
language models (LLMs) is the assumption that models can improve by reflecting on past mistakes. We study a phenomenon termed contextual drag: the presence of failed attempts in the context biases subsequent generations toward structurally similar errors. Across evaluations of 11 proprietary and open-weight models on 8
reasoning tasks, contextual drag induces 10-20% performance drops, and iterative self-refinement in models with severe contextual drag can collapse into self-deterioration. Structural analysis using tree edit distance reveals that subsequent
reasoning trajectories inherit structurally similar error patterns from the context. We demonstrate that neither external feedback nor successful self-verification suffices to eliminate this effect. While mitigation strategies such as fallback-behavior fine-tuning and context denoising yield partial improvements, they fail to fully restore baseline performance, positioning contextual drag as a persistent failure mode in current
reasoning architectures.
Read the full abstract ▾
All authors Yun Cheng, Xingyu Zhu, Haoyu Zhao, Sanjeev Arora
Computation and Language
ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation
Jiarui Jin, Haoyu Wang, Xingliang Wu et al. (+9 more)
Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing
multimodal large
language models (MLLMs) remain unreliable for ECG interpretation, often producing plausible but clinically incorrect analyses. To address this, we propose ECG-R1, the first
reasoning ECG MLLM designed for reliable ECG interpretation via three innovations. First, we construct the interpretation corpus using Protocol-Guided Instruction Data Generation, grounding interpretation in measurable ECG features and monograph-defined quantitative thresholds and diagnostic logic. Second, we present a modality-decoupled architecture with Interleaved Modality Dropout to improve robustness and cross-modal consistency when either the ECG signal or ECG image is missing. Third, we present Reinforcement Learning with ECG Diagnostic Evidence Rewards to strengthen evidence-grounded ECG interpretation. Additionally, we systematically evaluate the ECG interpretation capabilities of proprietary, open-source, and medical MLLMs, and provide the first quantitative evidence that severe
hallucinations are widespread, suggesting that the public should not directly trust these outputs without independent verification. Code is available at \href{https://github.com/PKUDigitalHealth/ECG-R1}{here}.
Read the full abstract ▾
All authors Jiarui Jin, Haoyu Wang, Xingliang Wu, Xiaocheng Fang, Xiang Lan, Zihan Wang, Deyun Zhang, Bo Liu, Yingying Zhang, Xian Wu, Hongyan Li, Shenda Hong
Computation and Language
Scaling Agentic Verifier for Competitive Coding
Zeyao Ma, Jing Zhang, Xiaokang Zhang et al. (+9 more)
Large
language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt. Execution-based re-ranking offers a promising test-time scaling strategy, yet existing methods are constrained by either difficult test case generation or inefficient random input sampling. To address this limitation, we propose Agentic Verifier, an execution-based
agent that actively reasons about program behaviors and searches for highly discriminative test inputs that expose behavioral discrepancies among candidate solutions. Through multi-turn interaction with code execution environments, the verifier iteratively refines the candidate input generator and produces targeted counterexamples rather than blindly sampling inputs. We train the verifier to acquire this discriminative input generation capability via a scalable pipeline combining large-scale data synthesis, rejection fine-tuning, and agentic reinforcement learning. Extensive experiments across five competitive programming
benchmarks demonstrate consistent improvements over strong execution-based baselines, achieving up to +10-15% absolute gains in Best@K accuracy. Further analysis reveals clear test-time scaling behavior and highlights the verifier's broader potential beyond reranking.
Read the full abstract ▾
All authors Zeyao Ma, Jing Zhang, Xiaokang Zhang, Jiaxi Yang, Zongmeng Zhang, Jiajun Zhang, Yuheng Jing, Lei Zhang, Hao Zheng, Wenting Zhao, Junyang Lin, Binyuan Hui
Computation and Language · Cross-listed from cs.AI
Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree Search
Hao Lu, Haoyuan Huang, Yulin Zhou et al. (+2 more)
Inference-time scaling strategies, particularly Monte Carlo Tree Search (MCTS), have significantly enhanced the
reasoning capabilities of Large
Language Models (LLMs). However, current approaches remain predominantly stateless, discarding successful
reasoning patterns after each problem instance and failing to mimic the empirical accumulation of wisdom characteristic of human problem-solving. To bridge this gap, we introduce Empirical-MCTS, a dual-loop framework that transforms stateless search into a continuous, non-parametric learning process. The framework unifies local exploration with global
memory optimization through two novel mechanisms: Pairwise-Experience-Evolutionary Meta-Prompting (PE-EMP) and a
Memory Optimization
Agent. PE-EMP functions as a reflexive optimizer within the local search, utilizing pairwise feedback to dynamically synthesize adaptive criteria and evolve meta-
prompts (system
prompts) in real-time. Simultaneously, the
Memory Optimization
Agent manages a global repository as a dynamic policy prior, employing atomic operations to distill high-quality insights across problems. Extensive evaluations on complex
reasoning benchmarks, including AIME25, ARC-AGI-2, and MathArena Apex, demonstrate that Empirical-MCTS significantly outperforms both stateless MCTS strategies and standalone experience-driven
agents. These results underscore the critical necessity of coupling structured search with empirical accumulation for mastering complex, open-ended
reasoning tasks.
Read the full abstract ▾
All authors Hao Lu, Haoyuan Huang, Yulin Zhou, Chen Li, Ningxin Zhu
Computation and Language
DementiaBank-Emotion: A Multi-Rater Emotion Annotation Corpus for Alzheimer's Disease Speech (Version 1.0)
Cheonkam Jeong, Jessica Liao, Audrey Lu et al. (+16 more)
We present DementiaBank-
Emotion, the first multi-rater
emotion annotation corpus for Alzheimer's disease (AD)
speech. Annotating 1,492 utterances from 108 speakers for Ekman's six basic
emotions and neutral, we find that AD patients express significantly more non-neutral
emotions (16.9%) than healthy controls (5.7%; p < .001). Exploratory acoustic analysis suggests a possible dissociation: control speakers showed substantial F0 modulation for sadness (Delta = -3.45 semitones from baseline), whereas AD speakers showed minimal change (Delta = +0.11 semitones; interaction p = .023), though this finding is based on limited samples (sadness: n=5 control, n=15 AD) and requires replication. Within AD
speech, loudness differentiates
emotion categories, indicating partially preserved
emotion-prosody mappings. We release the corpus, annotation guidelines, and calibration workshop materials to support research on
emotion recognition in clinical populations.
Read the full abstract ▾
All authors Cheonkam Jeong, Jessica Liao, Audrey Lu, Yutong Song, Christopher Rashidian, Donna Krogh, Erik Krogh, Mahkameh Rasouli, Jung-Ah Lee, Nikil Dutt, Lisa M Gibbs, David Sultzer, Julie Rousseau, Jocelyn Ludlow, Margaret Galvez, Alexander Nuth, Chet Khay, Sabine Brunswicker, Adeline Nyamathi
Computation and Language
CoLT: Reasoning with Chain of Latent Tool Calls
Fangwei Zhu and Zhifang Sui
Chain-of-Thought (CoT) is a critical technique in enhancing the
reasoning ability of Large
Language Models (LLMs), and latent
reasoning methods have been proposed to accelerate the inefficient
token-level
reasoning chain. We notice that existing latent
reasoning methods generally require model structure augmentation and exhaustive training, limiting their broader applicability. In this paper, we propose CoLT, a novel framework that implements latent
reasoning as “tool calls”. Instead of
reasoning entirely in the latent space, CoLT generates seed
tokens that contain information of a
reasoning step. When a latent tool call is triggered, a smaller external model will take the hidden states of seed
tokens as its input, and unpack the seed
tokens back to a full
reasoning step. In this way, we can ensure that the main model reasons in the explicit
token space, preserving its ability while improving efficiency. Experimental results on four mathematical
datasets demonstrate that CoLT achieves higher accuracy and shorter
reasoning length than baseline latent models, and is compatible with reinforcement learning
algorithms and different decoder structures.
Read the full abstract ▾
Computation and Language
Tokenization and Morphological Fidelity in Uralic NLP: A Cross-Lingual Evaluation
Nuo Xu and Ahrii Kim
Subword tokenization critically affects Natural
Language Processing (NLP) performance, yet its behavior in morphologically rich and low-resource
language families remains under-explored. This study systematically compares three subword paradigms – Byte Pair Encoding (BPE), Overlap BPE (OBPE), and Unigram
Language Model – across six Uralic
languages with varying resource availability and typological diversity. Using part-of-
speech (POS) tagging as a controlled downstream task, we show that OBPE consistently achieves stronger morphological
alignment and higher tagging accuracy than conventional methods, particularly within the Latin-script group. These gains arise from reduced fragmentation in open-class categories and a better balance across the frequency spectrum. Transfer efficacy further depends on the downstream tagging architecture, interacting with both training volume and genealogical proximity. Taken together, these findings highlight that morphology-sensitive tokenization is not merely a preprocessing choice but a decisive factor in enabling effective cross-lingual transfer for agglutinative, low-resource
languages.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning
Zeming Wei, Qiaosheng Zhang, Xia Hu et al. (+1 more)
Large
Reasoning Models (LRMs) have achieved tremendous success with their chain-of-thought (CoT)
reasoning, yet also face safety issues similar to those of basic
language models. In particular, while
algorithms are designed to guide them to deliberately refuse harmful
prompts with safe
reasoning, this process often fails to generalize against diverse and complex jailbreak attacks. In this work, we attribute these failures to the generalization of the safe
reasoning process, particularly their insufficiency against complex attack
prompts. We provide both theoretical and empirical evidence to show the necessity of a more sufficient safe
reasoning process to defend against advanced attack
prompts. Building on this insight, we propose a Risk-Aware Preference Optimization (RAPO) framework that enables LRM to adaptively identify and address the safety risks with appropriate granularity in its thinking content. Extensive experiments demonstrate that RAPO successfully generalizes multiple LRMs' safe
reasoning adaptively across diverse attack
prompts whilst preserving general utility, contributing a robust
alignment technique for LRM safety. Our code is available at https://github.com/weizeming/RAPO.
Read the full abstract ▾
All authors Zeming Wei, Qiaosheng Zhang, Xia Hu, Xingcheng Xu
Computation and Language · Cross-listed from cs.SD
Frontend Token Enhancement for Token-Based Speech Recognition
Takanori Ashihara, Shota Horiguchi, Kohei Matsuura et al. (+2 more)
Discretized representations of
speech signals are efficient alternatives to continuous features for various
speech applications, including automatic
speech recognition (ASR) and
speech language models. However, these representations, such as semantic or phonetic
tokens derived from clustering outputs of self-supervised learning (SSL)
speech models, are susceptible to environmental noise, which can degrade backend task performance. In this work, we introduce a frontend system that estimates clean
speech tokens from noisy
speech and evaluate it on an ASR backend using semantic
tokens. We consider four types of enhancement models based on their input/output domains: wave-to-wave,
token-to-
token, continuous SSL features-to-
token, and wave-to-
token. These models are trained independently of ASR backends. Experiments on the CHiME-4
dataset demonstrate that wave-to-
token enhancement achieves the best performance among the frontends. Moreover, it mostly outperforms the ASR system based on continuous SSL features.
Read the full abstract ▾
All authors Takanori Ashihara, Shota Horiguchi, Kohei Matsuura, Tsubasa Ochiai, Marc Delcroix
Computation and Language
Language Models Struggle to Use Representations Learned In-Context
Michael A. Lepori, Tal Linzen, Ann Yuan et al. (+1 more)
Though large
language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier goals of artificial intelligence research: creating an artificial system that can adapt its behavior to radically new contexts upon deployment. One important step towards this goal is to create systems that can induce rich representations of data that are seen in-context, and then flexibly deploy these representations to accomplish goals. Recently, Park et al. (2024) demonstrated that current LLMs are indeed capable of inducing such representation from context (i.e., in-context representation learning). The present study investigates whether LLMs can use these representations to complete simple downstream tasks. We first assess whether open-weights LLMs can use in-context representations for next-
token prediction, and then probe models using a novel task, adaptive world modeling. In both tasks, we find evidence that open-weights LLMs struggle to deploy representations of novel semantics that are defined in-context, even if they encode these semantics in their latent representations. Furthermore, we assess closed-source, state-of-the-art
reasoning models on the adaptive world modeling task, demonstrating that even the most performant LLMs cannot reliably leverage novel patterns presented in-context. Overall, this work seeks to inspire novel methods for encouraging models to not only encode information presented in-context, but to do so in a manner that supports flexible deployment of this information.
Read the full abstract ▾
All authors Michael A. Lepori, Tal Linzen, Ann Yuan, Katja Filippova
Computation and Language
Enforcing Monotonic Progress in Legal Cross-Examination: Preventing Long-Horizon Stagnation in LLM-Based Inquiry
Hsien-Jyh Liao
Large
language models (LLMs) exhibit impressive linguistic fluency but struggle to reliably complete long-horizon tasks under explicit procedural constraints. In legal cross-examination, purely proba-bilistic generation often maintains behavioral coherence while failing to ensure procedural advancement. We characterize this failure as procedural stagnation and propose Soft-FSM, a neuro-symbolic architecture that enforces monotonic progress over accumulated Key Information Units (KIUs) via an external deterministic state controller. Experiments on three real-world Taiwanese criminal homicide cases show that baseline methods collapse below 40% completeness, while Soft-FSM consistently achieves over 97% with near-zero redundancy. These results suggest that, in such domains, reliable task completion cannot be guaranteed by emergent LLM behavior alone, and can be reliably enforced through explicit and verifiable external state control.
Read the full abstract ▾
Computation and Language
From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM Agents
Xinyue Wang, Yuanhe Zhang, Zhengshuo Gong et al. (+6 more)
The enhanced capabilities of LLM-based
agents come with an emergency for model planning and tool-use abilities. Attributing to helpful-harmless trade-off from LLM
alignment,
agents typically also inherit the flaw of "over-refusal", which is a passive failure mode. However, the proactive planning and action capabilities of
agents introduce another crucial danger on the other side of the trade-off. This phenomenon we term "Toxic Proactivity”: an active failure mode in which an
agent, driven by the optimization for Machiavellian helpfulness, disregards ethical constraints to maximize utility. Unlike over-refusal, Toxic Proactivity manifests as the
agent taking excessive or manipulative measures to ensure its "usefulness” is maintained. Existing research pays little
attention to identifying this behavior, as it often lacks the subtle context required for such strategies to unfold. To reveal this risk, we introduce a novel evaluation framework based on dilemma-driven interactions between dual models, enabling the simulation and analysis of
agent behavior over multi-step behavioral trajectories. Through extensive experiments with mainstream LLMs, we demonstrate that Toxic Proactivity is a widespread behavioral phenomenon and reveal two major tendencies. We further present a systematic
benchmark for evaluating Toxic Proactive behavior across contextual settings.
Read the full abstract ▾
All authors Xinyue Wang, Yuanhe Zhang, Zhengshuo Gong, Haoran Gao, Fanyu Meng, Zhenhong Zhou, Li Sun, Yang Liu, Sen Su
Computation and Language
The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment
Zhexin Zhang, Yida Lu, Junfeng Fang et al. (+8 more)
Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training remain largely unexplored. Beyond explicit reward hacking that directly manipulates explicit reward functions in reinforcement learning, we study implicit training-time safety risks: harmful behaviors driven by a model's internal incentives and contextual background information. For example, during code-based reinforcement learning, a model may covertly manipulate logged accuracy for self-preservation. We present the first systematic study of this problem, introducing a taxonomy with five risk levels, ten fine-grained risk categories, and three incentive types. Extensive experiments reveal the prevalence and severity of these risks: notably, Llama-3.1-8B-Instruct exhibits risky behaviors in 74.4% of training runs when provided only with background information. We further analyze factors influencing these behaviors and demonstrate that implicit training-time risks also arise in multi-
agent training settings. Our results identify an overlooked yet urgent safety challenge in training.
Read the full abstract ▾
All authors Zhexin Zhang, Yida Lu, Junfeng Fang, Junxiao Yang, Shiyao Cui, Hao Zhou, Fandong Meng, Jie Zhou, Hongning Wang, Minlie Huang, Tat-Seng Chua