Computation and Language
Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search
Zhiyu Cao, Peifeng Li and Qiaoming Zhu
Conversational Query Rewriting (CQR) aims to rewrite ambiguous queries to achieve more efficient conversational search. Early studies have predominantly focused on the rewriting in isolation, ignoring the feedback from query rewrite, passage
retrieval and response generation in the rewriting process. To address this issue, we propose Multi-Faceted Self-Consistent Preference Aligned CQR (MSPA-CQR). Specifically, we first construct self-consistent preference
alignment data from three dimensions (rewriting,
retrieval, and response) to generate more diverse rewritten queries. Then we propose prefix guided multi-faceted direct preference optimization to learn preference information from three different dimensions. The experimental results show that our MSPA-CQR is effective in both in- and out-of-distribution scenarios.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
Geometric Properties of the Voronoi Tessellation in Latent Semantic Manifolds of Large Language Models
Marshall Brett
Language models operate on discrete
tokens but compute in continuous vector spaces, inducing a Voronoi tessellation over the representation
manifold. We study this tessellation empirically on Qwen3.5-4B-Base, making two contributions. First, using float32 margin recomputation to resolve bfloat16 quantization artifacts, we validate Mabrok's (2026) linear scaling law of the expressibility gap with $R^2$ = 0.9997 - the strongest confirmation to date - and identify a mid-layer
geometric ambiguity regime where margin geometry is anti-correlated with cross-
entropy (layers 24-28, $\rho$ = -0.29) before crystallizing into
alignment at the final layer ($\rho$ = 0.836). Second, we show that the Voronoi tessellation of a converged model is reshapable through margin refinement procedures (MRP): short post-hoc optimization runs that widen
token-decision margins without retraining. We compare direct margin maximization against Fisher information distance maximization across a dose-response sweep. Both methods find the same ceiling of ~16,300 correctable positions per 256K evaluated, but differ critically in collateral damage. Margin maximization damage escalates with intervention strength until corrections are overwhelmed. Fisher damage remains constant at ~5,300 positions across the validated range ($\lambda$ = 0.15-0.6), achieving +28% median margin improvement at $\lambda$ = 0.6 with invariant downstream
benchmarks - a
geometric reorganization that compresses the expressibility gap while preserving its scaling law. However, frequency and
token-class audits reveal that gains concentrate in high-frequency structural
tokens (84% of net corrections at $\lambda$ = 0.6), with content and entity-like contributions shrinking at higher $\lambda$. Fisher MRP is therefore a viable
geometric polishing tool whose practical ceiling is set not by aggregate damage but by the uniformity of
token-level benefit.
Read the full abstract ▾
Computation and Language
TeamLLM: A Human-Like Team-Oriented Collaboration Framework for Multi-Step Contextualized Tasks
Xiangyu Wang, Jin Wu, Haoran Shi et al. (+3 more)
Recently, multi-Large
Language Model (LLM) frameworks have been proposed to solve contextualized tasks. However, these frameworks do not explicitly emulate human team role division, which may lead to a single perspective, thereby weakening performance on multi-step contextualized tasks. To address this issue, we propose TeamLLM, a human-like Team-Oriented Multi-LLM Collaboration Framework. TeamLLM adopts four team roles with distinct division and employs a three-phase multi-LLM collaboration for multi-step contextualized tasks. To evaluate the effectiveness of TeamLLM on multi-step contextualized tasks, we propose Contextually-Grounded and Procedurally-Structured tasks (CGPST) and construct the CGPST
benchmark. This
benchmark has four core features: contextual grounding, procedural structure, process-oriented evaluation and multi-dimensional assessment. We evaluate ten popular LLMs on CGPST at overall-level, step-level, and dimension-level. Results show that TeamLLM substantially improves performance on CGPST. We release the
benchmark with scenarios, full-process responses and human scores from ten LLMs. The code and data are available at https://anonymous.4open.science/r/TeamLLM-anonymous-C50E/.
Read the full abstract ▾
All authors Xiangyu Wang, Jin Wu, Haoran Shi, Wei Xia, Jiarui Yu, Chanjin Zheng
Computation and Language
Multilingual Cognitive Impairment Detection in the Era of Foundation Models
Damar Hoogland, Boshko Koloski, Jaya Caporusso et al. (+5 more)
We evaluate cognitive impairment (CI) classification from transcripts of
speech in English, Slovene, and Korean. We compare zero-shot large
language models (LLMs) used as direct classifiers under three input settings – transcript-only, linguistic-features-only, and combined – with supervised tabular approaches trained under a leave-one-out protocol. The tabular models operate on engineered linguistic features, transcript
embeddings, and early or late fusion of both modalities. Across
languages, zero-shot LLMs provide competitive no-training baselines, but supervised tabular models generally perform better, particularly when engineered linguistic features are included and combined with
embeddings. Few-shot experiments focusing on
embeddings indicate that the value of limited supervision is
language-dependent, with some
languages benefiting substantially from additional labelled examples while others remain constrained without richer feature representations. Overall, the results suggest that, in small-data CI detection, structured linguistic signals and simple fusion-based classifiers remain strong and reliable signals.
Read the full abstract ▾
All authors Damar Hoogland, Boshko Koloski, Jaya Caporusso, Tine Kolenik, Ana Zwitter Vitez, Senja Pollak, Christina Manouilidou, Matthew Purver
Computation and Language
How Long Reasoning Chains Influence LLMs' Judgment of Answer Factuality
Minzhu Tu, Shiyu Ni and Keping Bi
Large
language models (LLMs) has been widely adopted as a scalable surrogate for human evaluation, yet such judges remain imperfect and susceptible to surface-level biases. One possible reason is that these judges lack sufficient information in assessing answer correctness. With the rise of
reasoning-capable models, exposing a generator's
reasoning content to the judge provides richer information and is a natural candidate for improving judgment accuracy. However, its actual impact on judge behavior remains understudied. In this paper, we systematically investigate how access to
reasoning chains affects LLM-based judgment across factual question answering (QA) and mathematical
reasoning benchmarks. We find that weak judges are easily swayed by
reasoning presence, frequently accepting incorrect answers accompanied by fluent
reasoning, while strong judges can partially leverage
reasoning as informative evidence. Nevertheless, even strong judges are misled by seemingly high-quality
reasoning chains. Controlled experiments further reveal that both fluency and factuality of
reasoning chains are critical signals driving judge decisions. These findings highlight the need for more robust LLM judges that can distinguish genuine
reasoning quality from superficial fluency when evaluating modern
reasoning models.
Read the full abstract ▾
Computation and Language
Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents
Heng Zhou, Zelin Tan, Zhemeng Zhang et al. (+15 more)
When an LLM-based
agent improves on a task, is the gain from the model itself or from the
reasoning paradigm wrapped around it? We study this question by comparing six inference-time paradigms, namely Direct, CoT, ReAct, Plan-Execute, Reflection, and ReCode, across four frontier LLMs and ten
benchmarks, yielding roughly 18,000 runs. We find that
reasoning structure helps dramatically on some tasks but hurts on others: ReAct improves over Direct by 44pp on
GAIA, while CoT degrades performance by 15pp on HumanEval. No single paradigm dominates, and oracle per-task selection beats the best fixed paradigm by 17.1pp on average. Motivated by this complementarity, we propose a select-then-solve approach: before answering each task, a lightweight
embedding-based router selects the most suitable paradigm. Across four models, the router improves average accuracy from 47.6% to 53.1%, outperforming the best fixed paradigm at 50.3% by 2.8pp and recovering up to 37% of the oracle gap. In contrast, zero-shot self-routing only works for GPT-5 at 67.1% and fails for weaker models, all trailing the learned router. Our results argue that
reasoning paradigm selection should be a per-task decision made by a learned router, not a fixed architectural choice.
Read the full abstract ▾
All authors Heng Zhou, Zelin Tan, Zhemeng Zhang, Yutao Fan, Yibing Lin, Li Kang, Xiufeng Song, Rui Li, Songtao Huang, Ao Yu, Yuchen Fan, Yanxu Chen, Kaixin Xu, Xiaohong Liu, Yiran Qin, Philip Torr, Chen Zhang, Zhenfei Yin
Computation and Language
StructKV: Preserving the Structural Skeleton for Scalable Long-Context Inference
Zhirui Chen, Peiyang Liu and Ling Shao
As Large
Language Models (LLMs) scale to support context windows exceeding one million
tokens, the linear growth of Key-Value (KV) cache imposes severe
memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context inference. Existing compression approaches typically prioritize
tokens based on local saliency metrics to decouple prefill computation from decoding
memory. However, these methods often rely on local saliency snapshots at a specific layer, thereby systematically discarding
tokens that act as global information hubs across the network depth but appear temporarily dormant at the specific layer selected for
pruning. To address this limitation, we propose StructKV, a structure-aware KV cache compression framework that introduces three core innovations: First, Global In-Degree Centrality aggregates
attention patterns across the network depth to identify global information hubs. Second, Dynamic Pivot Detection utilizes information-theoretic metrics to adaptively locate the optimal layer for compression. Finally, Structural Propagation and Decoupling separates the computational budget from the
memory storage budget. Experimental results on the LongBench and RULER
benchmarks demonstrate that StructKV effectively preserves long-range dependencies and
retrieval robustness.
Read the full abstract ▾
Computation and Language
WisdomInterrogatory (LuWen): An Open-Source Legal Large Language Model Technical Report
Yiquan Wu, Yuhang Liu, Yifei Liu et al. (+4 more)
Large
language models have demonstrated remarkable capabilities across a wide range of natural
language processing tasks, yet their application in the legal domain remains challenging due to the specialized terminology, complex
reasoning requirements, and rapidly evolving legal knowledge involved. In this paper, we present WisdomInterrogatory (LuWen), an open-source Chinese legal
language model built upon the Baichuan foundation model through three key techniques: continual pre-training on a large-scale legal corpus, supervised fine-tuning with carefully curated legal instruction data, and
retrieval-augmented generation integrated with a comprehensive legal knowledge base. We evaluate LuWen on five representative legal tasks spanning both prediction and generation settings, including legal judgment prediction, judicial examination, legal text summarization, law article question answering, and judicial decision
reasoning. Experimental results show that LuWen outperforms several strong baselines, demonstrating the effectiveness of our approach in adapting general-purpose
language models to the legal domain.
Read the full abstract ▾
All authors Yiquan Wu, Yuhang Liu, Yifei Liu, Ang Li, Siying Zhou, Kun Kuang, Fei Wu
Computation and Language
SQLStructEval: Structural Evaluation of LLM Text-to-SQL Generation
Yixi Zhou, Fan Zhang, Zhiqiao Guo et al. (+4 more)
In Text-to-SQL tasks, large
language models can generate structurally different SQL queries that return correct answers for the same intent. We call this phenomenon execution-correct structural divergence (ECSD). We introduce SQLStructEval, a framework that analyzes this behavior through canonical abstract syntax tree representations. We quantify structural diversity and agreement across generations. Experiments with different LLMs on multiple Text-to-SQL
datasets, including Spider, document ECSD across models and
datasets. Furthermore, our experiments demonstrate that generated queries are sensitive to question paraphrases and schema presentation. To address ECSD, we adopt a pipeline that first generates structured intermediate representations and then deterministically compiles them into SQL, improving execution accuracy and structural agreement among correct outputs. Structural analysis thus provides an additional diagnostic perspective that complements execution-based evaluation. Code is available at https://xanderzhou2022.github.io/AACL2026-SQLSTRUCTEVAL/.
Read the full abstract ▾
All authors Yixi Zhou, Fan Zhang, Zhiqiao Guo, Yu Chen, Haipeng Zhang, Preslav Nakov, Zhuohan Xie
Computation and Language
TEC: A Collection of Human Trial-and-error Trajectories for Problem Solving
Xinkai Zhang, Jingtao Zhan, Yiqun Liu et al. (+1 more)
Trial-and-error is a fundamental strategy for humans to solve complex problems and a necessary capability for Artificial Intelligence (AI) systems operating in real-world environments. Although several trial-and-error AI techniques have recently been proposed, most of them rely on simple heuristics designed by researchers and achieve limited performance gains. The core issue is the absence of appropriate data: current models cannot learn from detailed records of how humans actually conduct trial-and-error in practice. To address this gap, we introduce a data annotation platform and a corresponding
dataset, termed Trial-and-Error Collection (TEC). The platform records users' complete trajectories across multiple trials and collects their reflections after receiving error feedback. Using this platform, we record the problem-solving processes of 46 participants on 58 tasks, resulting in 5,370 trial trajectories along with error reflections across 41,229 webpages. With this
dataset, we observe that humans achieve substantially higher accuracy compared to LLMs, which demonstrates that humans are more effective in trial-and-error than LLMs. We believe that the TEC platform and
dataset provide a valuable foundation for understanding human trial-and-error behavior and for developing more capable AI systems. Platform and
dataset are publicly available.
Read the full abstract ▾
All authors Xinkai Zhang, Jingtao Zhan, Yiqun Liu, Qingyao Ai
Computation and Language · Cross-listed from cs.AI
Jianhong Pang, Ruoxi Cheng, Ziyi Ye et al. (+4 more)
AI applications driven by
multimodal large
language models (MLLMs) are prone to
hallucinations and pose considerable risks to human users. Crucially, such
hallucinations are not equally problematic: some
hallucination contents could be detected by human users(i.e., obvious
hallucinations), while others are often missed or require more verification effort(i.e., elusive
hallucinations). This indicates that
multimodal AI
hallucinations vary significantly in their verifiability. Yet, little research has explored how to control this property for AI applications with diverse security and usability demands. To address this gap, we construct a
dataset from 4,470 human responses to AI-generated
hallucinations and categorize these
hallucinations into obvious and elusive types based on their verifiability by human users. Further, we propose an activation-space intervention method that learns separate probes for obvious and elusive
hallucinations. We reveal that obvious and elusive
hallucinations elicit different intervention probes, allowing for fine-grained control over the model's verifiability. Empirical results demonstrate the efficacy of this approach and show that targeted interventions yield superior performance in regulating corresponding verifiability. Moreover, simply mixing these interventions enables flexible control over the verifiability required for different scenarios.
Read the full abstract ▾
All authors Jianhong Pang, Ruoxi Cheng, Ziyi Ye, Xingjun Ma, Zuxuan Wu, Xuanjing Huang, Yu-Gang Jiang
Computation and Language · Cross-listed from cs.CV
Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentation
Jianing Zhang, Runan Li, Honglin Pang et al. (+5 more)
Deciphering ancient Chinese Oracle Bone Script (OBS) is a challenging task that offers insights into the beliefs, systems, and culture of the ancient era. Existing approaches treat decipherment as a closed-set image recognition problem, which fails to bridge the “interpretation gap”: while individual characters are often unique and rare, they are composed of a limited set of recurring, pictographic components that carry transferable semantic meanings. To leverage this structural logic, we propose an
agent-driven
Vision-
Language Model (VLM) framework that integrates a VLM for precise visual grounding with an LLM-based
agent to automate a
reasoning chain of component identification, graph-based knowledge
retrieval, and relationship inference for linguistically accurate interpretation. To support this, we also introduce OB-Radix, an expert-annotated
dataset providing structural and semantic data absent from prior corpora, comprising 1,022 character images (934 unique characters) and 1,853 fine-grained component images across 478 distinct components with verified explanations. By evaluating our system across three
benchmarks of different tasks, we demonstrate that our framework yields more detailed and precise decipherments compared to baseline methods.
Read the full abstract ▾
All authors Jianing Zhang, Runan Li, Honglin Pang, Ding Xia, Zhou Zhu, Qian Zhang, Chuntao Li, Xi Yang
Computation and Language
Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs
Haoyue Liu, Zhichao Wang, Yongxin Guo et al. (+2 more)
Automated
prompt optimization is crucial for eliciting reliable
reasoning from large
language models (LLMs), yet most API-only
prompt optimizers iteratively edit monolithic
prompts, coupling components and obscuring credit assignment, limiting controllability, and wasting
tokens. We propose Adaptive
Prompt Structure Factorization (aPSF), an API-only framework (
prompt-in/text-out; no access to model internals) that uses an Architect model to discover task-specific
prompt structures as semantic factors. aPSF then performs interventional, single-factor updates: interventional factor-level scoring estimates each factor's marginal contribution via validation-performance changes, and error-guided factor selection routes updates to the current dominant failure source for more sample-efficient optimization. Across multiple advanced
reasoning benchmarks, aPSF outperforms strong baselines including principle-aware optimizers, improving accuracy by up to +2.16 percentage points on average, and reduces optimization cost by 45–87%
tokens on MultiArith while reaching peak validation in 1 step.
Read the full abstract ▾
All authors Haoyue Liu, Zhichao Wang, Yongxin Guo, Haoran Shou, Xiaoying Tang
Computation and Language
ChemVLR: Prioritizing Reasoning in Perception for Chemical Vision-Language Understanding
Xuanle Zhao, Xinyuan Cai, Xiang Cheng et al. (+2 more)
While
Vision-
Language Models (VLMs) have demonstrated significant potential in chemical visual understanding, current models are predominantly optimized for direct visual question-answering tasks. This paradigm often results in "black-box" systems that fail to utilize the inherent capability of Large
Language Models (LLMs) to infer underlying reaction mechanisms. In this work, we introduce ChemVLR, a chemical VLM designed to prioritize
reasoning within the perception process. Unlike conventional chemical VLMs, ChemVLR analyzes visual inputs in a fine-grained manner by explicitly identifying granular chemical descriptors, such as functional groups, prior to generating answers. This approach ensures the production of explicit and interpretable
reasoning paths for complex visual chemical problems. To facilitate this methodology, we implement a cross-modality reverse-engineering strategy, combined with a rigorous filtering pipeline, to curate a large-scale
reasoning-and-captioning
dataset comprising 760k high-quality samples across molecular and reaction tasks. Furthermore, we adopt a three-stage training framework that systemically builds model perception and
reasoning capacity. Experiments demonstrate that ChemVLR achieves state-of-the-art (SOTA) performance, surpassing both leading proprietary models and domain-specific open-source baselines. We also provide comprehensive ablation studies to validate our training strategy and data generation designs. Code and model weights will be available at https://github.com/xxlllz/ChemVLR.
Read the full abstract ▾
All authors Xuanle Zhao, Xinyuan Cai, Xiang Cheng, Xiuyi Chen, Bo Xu
Computation and Language
Between Century and Poet: Graph-Based Lexical Semantic Change in Persian Poetry
Kourosh Shahnazari, Seyed Moein Ayyoubzadeh and Mohammadali Keshtparvar
Meaning in Persian poetry is both historical and relational. Words persist through literary tradition while shifting their force through changing constellations of neighbors, rhetorical frames, and poetic voices. This study examines that process using aligned Word2Vec spaces combined with graph-based neighborhood analysis across centuries and major poets. Rather than modeling semantic change as vector displacement alone, it treats lexical history as the rewiring of local semantic graphs: the gain and loss of neighbors, shifts in bridge roles, and movement across communities. The analysis centers on twenty target words, anchored by five recurrent reference terms: Earth, Night, two wine terms, and Heart. Surrounding them are affective, courtly, elemental, and Sufi concepts such as Love, Sorrow, Dervish, King, Annihilation, and Truth. These words exhibit distinct patterns of change. Night is more time-sensitive, Earth more poet-sensitive, and Heart shows continuity despite graph-role mobility. The two wine terms highlight probe sensitivity: one is broad and semantically diffuse, while the other is narrower and more stable. A lexical audit confirms that the corpus contains historically driven terms, poet-specific usages, and sparsely attested mystical vocabulary requiring caution. Overall, semantic change in Persian poetry is better captured as neighborhood rewiring than as abstract drift. For Digital Humanities, this approach restores local structure to computational analysis and supports interpretations closer to literary practice: persistence, migration, mediation, and selective transformation.
Read the full abstract ▾
Computation and Language
A Graph-Enhanced Defense Framework for Explainable Fake News Detection with LLM
Bo Wang, Jing Ma, Hongzhan Lin et al. (+4 more)
Explainable fake news detection aims to assess the veracity of news claims while providing human-friendly explanations. Existing methods incorporating investigative journalism are often inefficient and struggle with breaking news. Recent advances in large
language models (LLMs) enable leveraging externally retrieved reports as evidence for detection and explanation generation, but unverified reports may introduce inaccuracies. Moreover, effective explainable fake news detection should provide a comprehensible explanation for all aspects of a claim to assist the public in verifying its accuracy. To address these challenges, we propose a graph-enhanced defense framework (G-Defense) that provides fine-grained explanations based solely on unverified reports. Specifically, we construct a claim-centered graph by decomposing the news claim into several sub-claims and modeling their dependency relationships. For each sub-claim, we use the
retrieval-augmented generation (RAG) technique to retrieve salient evidence and generate competing explanations. We then introduce a defense-like inference module based on the graph to assess the overall veracity. Finally, we
prompt an LLM to generate an intuitive explanation graph. Experimental results demonstrate that G-Defense achieves state-of-the-art performance in both veracity detection and the quality of its explanations.
Read the full abstract ▾
All authors Bo Wang, Jing Ma, Hongzhan Lin, Zhiwei Yang, Ruichao Yang, Yuan Tian, Yi Chang
Computation and Language
A Parameter-Efficient Transfer Learning Approach through Multitask Prompt Distillation and Decomposition for Clinical NLP
Cheng Peng, Mengxian Lyu, Ziyi Chen et al. (+1 more)
Existing
prompt-based fine-tuning methods typically learn task-specific
prompts independently, imposing significant computing and storage overhead at scale when deploying multiple clinical natural
language processing (NLP) systems. We present a multitask
prompt distillation and decomposition framework that learns a single shared metaprompt from 21 diverse clinical source tasks and adapts it to unseen target tasks with fewer than 0.05% trainable parameters. Evaluated across five clinical NLP task types (named entity recognition, relation extraction, question answering, natural
language inference, and summarization) on 10 held-out target
datasets using three backbone models (LLaMA 3.1 8B, Meditron3 8B, gpt-oss 20B), our framework consistently outperforms LoRA by 1.5~1.7% despite using orders of magnitude fewer parameters, and exceeds single-task
prompt tuning by 6.1~6.6%. The gpt-oss 20B model achieves the highest overall performance, particularly on clinical
reasoning tasks. The strong zero- and few-shot performance demonstrates better transferability of the shared
prompt representation.
Read the full abstract ▾
All authors Cheng Peng, Mengxian Lyu, Ziyi Chen, Yonghui Wu
Computation and Language
Feedback Adaptation for Retrieval-Augmented Generation
Jihwan Bang, Seunghan Yang, Kyuhong Shim et al. (+3 more)
Retrieval-Augmented Generation (RAG) systems are typically evaluated under static assumptions, despite being frequently corrected through user or expert feedback in deployment. Existing evaluation protocols focus on overall accuracy and fail to capture how systems adapt after feedback is introduced. We introduce feedback adaptation as a problem setting for RAG systems, which asks how effectively and how quickly corrective feedback propagates to future queries. To make this behavior measurable, we propose two evaluation axes: correction lag, which captures the delay between feedback provision and behavioral change, and post-feedback performance, which measures reliability on semantically related queries after feedback. Using these metrics, we show that training-based approaches exhibit a trade-off between delayed correction and reliable adaptation. We further propose PatchRAG, a minimal inference-time instantiation that incorporates feedback without retraining, demonstrating immediate correction and strong post-feedback generalization under the proposed evaluation. Our results highlight feedback adaptation as a previously overlooked dimension of RAG system behavior in interactive settings.
Read the full abstract ▾
All authors Jihwan Bang, Seunghan Yang, Kyuhong Shim, Simyung Chang, Juntae Lee, Sungha Choi
Computation and Language · Cross-listed from cs.LG
SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning
Zhengyang Ai, Zikang Shan, Xiaodong Ai et al. (+3 more)
Process supervision has emerged as a promising approach for enhancing LLM
reasoning, yet existing methods fail to distinguish meaningful progress from mere verbosity, leading to limited
reasoning capabilities and unresolved
token inefficiency. To address this, we propose Stage-aware Hierarchical Advantage via Potential Estimation (SHAPE), a framework that formalizes
reasoning as a trajectory through a state space of empirical solvability. SHAPE introduces a hierarchical credit assignment mechanism: at the segment level, it employs a stage-aware advantage function to prioritize efficient breakthroughs in low-potential states; at the
token level, it utilizes
entropy-driven redistribution to sharpen execution signals. Extensive experiments in math
reasoning across three base models and five
benchmarks demonstrate that SHAPE achieves an average accuracy gain of 3% with 30% reduced
token consumption.
Read the full abstract ▾
All authors Zhengyang Ai, Zikang Shan, Xiaodong Ai, Jingxian Tang, Hangkai Hu, Pinyan Lu
Computation and Language · Cross-listed from cs.CR
Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection
Zi Liang, Qipeng Xie, Jun He et al. (+7 more)
Recent advancements in Large
Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST), primarily due to their superior contextual
reasoning capabilities compared to traditional symbolic or rule-based methods. However, existing LLM-based approaches typically attempt to replace human experts directly without integrating effectively with existing SAST tools. This lack of integration results in ineffectiveness, including high rates of false positives,
hallucinations, limited
reasoning depth, and excessive
token usage, making them impractical for industrial deployment. To overcome these limitations, we present a paradigm shift that reorchestrates the SAST workflow from current LLM-assisted structure to a new LLM-centered workflow. We introduce Argus (Agentic and
Retrieval-Augmented Guarding System), the first multi-
agent framework designed specifically for vulnerability detection. Argus incorporates three key novelties: comprehensive supply chain analysis, collaborative multi-
agent workflows, and the integration of state-of-the-art techniques such as
Retrieval-Augmented Generation (RAG) and ReAct to minimize
hallucinations and enhance
reasoning. Extensive empirical evaluation demonstrates that Argus significantly outperforms existing methods by detecting a higher volume of true vulnerabilities while simultaneously reducing false positives and operational costs. Notably, Argus has identified several critical zero-day vulnerabilities with CVE assignments.
Read the full abstract ▾
All authors Zi Liang, Qipeng Xie, Jun He, Bohuan Xue, Weizheng Wang, Yuandao Cai, Fei Luo, Boxian Zhang, Haibo Hu, Kaishun Wu
Computation and Language
Caleb Zheng, Jyotika Singh, Fang Tu et al. (+6 more)
In-Context Learning and Chain-of-Thought prompting improve
reasoning in large
language models (LLMs). These typically come at the cost of longer, more expensive
prompts that may contain redundant information.
Prompt compression based on
pruning offers a practical solution, yet existing methods rely on sequential
token removal which is computationally intensive. We present DiffuMask, a
diffusion-based framework integrating hierarchical shot-level and
token-level
pruning signals, that enables rapid and parallel
prompt pruning via iterative mask prediction. DiffuMask substantially accelerates the compression process via masking multiple
tokens in each denoising step. It offers tunable control over retained content, preserving essential
reasoning context and achieving up to 80%
prompt length reduction. Meanwhile, it maintains or improves accuracy across in-domain, out-of-domain, and cross-model settings. Our results show that DiffuMask provides a generalizable and controllable framework for
prompt compression, facilitating faster and more reliable in-context
reasoning in LLMs.
Read the full abstract ▾
All authors Caleb Zheng, Jyotika Singh, Fang Tu, Weiyi Sun, Sujeeth Bharadwaj, Yassine Benajiba, Sujith Ravi, Eli Shlizerman, Dan Roth
Computation and Language
The Detection-Extraction Gap: Models Know the Answer Before They Can Say It
Hanyang Wang and Mingxuan Zhu
Modern
reasoning models continue generating long after the answer is already determined. Across five model configurations, two families, and three
benchmarks, we find that 52–88% of chain-of-thought
tokens are produced after the answer is recoverable from a partial prefix. This post-commitment generation reveals a structural phenomenon: the detection-extraction gap. Free continuations from early prefixes recover the correct answer even at 10% of the trace, while forced extraction fails on 42% of these cases. The answer is recoverable from the model state, yet
prompt-conditioned decoding fails to extract it. We formalize this mismatch via a total-variation bound between free and forced continuation distributions, yielding quantitative estimates of suffix-induced shift. Exploiting this asymmetry, we propose Black-box Adaptive Early Exit (BAEE), which uses free continuations for both detection and extraction, truncating 70–78% of serial generation while improving accuracy by 1–5pp across all models. For thinking-mode models, early exit prevents post-commitment overwriting, yielding gains of up to 5.8pp; a cost-optimized variant achieves 68–73% reduction at a median of 9 API calls. Code is available at https://github.com/EdWangLoDaSc/know2say.
Read the full abstract ▾
Computation and Language
Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs
Maotian Ma, Zheni Zeng, Zhenghao Liu et al. (+1 more)
Large
language models (LLMs) have shown strong knowledge reserves and task-solving capabilities, but still face the challenge of severe
hallucination, hindering their practical application. Though scientific theories and rules can efficiently direct the behaviors of human manipulators, LLMs still do not utilize these highly-condensed knowledge sufficiently through training or prompting. To address this issue, we propose SciDC, an LLM generation method that integrate subject-specific knowledge with strong constraints. By adopting strong LLMs to automatically convert flexible knowledge into multi-layered, standardized rules, we build an extensible framework to effectively constrain the model generation on domain tasks. Experiments on scientific tasks including industrial formulation design, clinical tumor diagnosis and retrosynthesis planning, consistently demonstrate the effectiveness of our method, achieving a 12% accuracy improvement on average compared with vanilla generation. We further discuss the potential of LLMs in automatically inductively summarizing highly-condensed knowledge, looking ahead to practical solutions for accelerating the overall scientific research process. All the code of this paper can be obtained (https://github.com/Maotian-Ma/SciDC).
Read the full abstract ▾
All authors Maotian Ma, Zheni Zeng, Zhenghao Liu, Yukun Yan
Computation and Language
Scoring Edit Impact in Grammatical Error Correction via Embedded Association Graphs
Qiyuan Xiao, Xiaoman Wang and Yunshi Lan
A Grammatical Error Correction (GEC) system produces a sequence of edits to correct an erroneous sentence. The quality of these edits is typically evaluated against human annotations. However, a sentence may admit multiple valid corrections, and existing evaluation settings do not fully accommodate diverse application scenarios. Recent meta-evaluation approaches rely on human judgments across multiple references, but they are difficult to scale to large
datasets. In this paper, we propose a new task, Scoring Edit Impact in GEC, which aims to automatically estimate the importance of edits produced by a GEC system. To address this task, we introduce a scoring framework based on an embedded association graph. The graph captures latent dependencies among edits and syntactically related edits, grouping them into coherent groups. We then perform perplexity-based scoring to estimate each edit's contribution to sentence fluency. Experiments across 4 GEC
datasets, 4
languages, and 4 GEC systems demonstrate that our method consistently outperforms a range of baselines. Further analysis shows that the embedded association graph effectively captures cross-linguistic structural dependencies among edits.
Read the full abstract ▾
Computation and Language
LLM-based Schema-Guided Extraction and Validation of Missing-Person Intelligence from Heterogeneous Data Sources
Joshua Castillo and Ravi Mukkamala
Missing-person and child-safety investigations rely on heterogeneous case documents, including structured forms, bulletin-style posters, and narrative web profiles. Variations in layout, terminology, and data quality impede rapid triage, large-scale analysis, and search-planning workflows. This paper introduces the Guardian Parser Pack, an AI-driven parsing and normalization pipeline that transforms multi-source investigative documents into a unified, schema-compliant representation suitable for operational review and downstream spatial modeling. The proposed system integrates (i) multi-engine PDF text extraction with Optical Character Recognition (OCR) fallback, (ii) rule-based source identification with source-specific parsers, (iii) schema-first harmonization and validation, and (iv) an optional Large
Language Model (LLM)-assisted extraction pathway incorporating validator-guided repair and shared geocoding services. We present the system architecture, key implementation decisions, and output design, and evaluate performance using both gold-aligned extraction metrics and corpus-level operational indicators. On a manually aligned subset of 75 cases, the LLM-assisted pathway achieved substantially higher extraction quality than the deterministic comparator (F1 = 0.8664 vs. 0.2578), while across 517 parsed records per pathway it also improved aggregate key-field completeness (96.97% vs. 93.23%). The deterministic pathway remained much faster (mean runtime 0.03 s/record vs. 3.95 s/record for the LLM pathway). In the evaluated run, all LLM outputs passed initial schema validation, so validator-guided repair functioned as a built-in safeguard rather than a contributor to the observed gains. These results support controlled use of probabilistic AI within a schema-first, auditable pipeline for high-stakes investigative settings.
Read the full abstract ▾
Computation and Language
To Lie or Not to Lie? Investigating The Biased Spread of Global Lies by LLMs
Zohaib Khan, Mustafa Dogan, Ifeoma Okoh et al. (+6 more)
Misinformation is on the rise, and the strong writing capabilities of LLMs lower the barrier for malicious actors to produce and disseminate false information. We study how LLMs behave when prompted to spread misinformation across
languages and target countries, and introduce GlobalLies, a
multilingual parallel
dataset of 440 misinformation generation
prompt templates and 6,867 entities, spanning 8
languages and 195 countries. Using both human annotations and large-scale LLM-as-a-judge evaluations across hundreds of thousands of generations from state-of-the-art models, we show that misinformation generation varies systematically based on the country being discussed. Propagation of lies by LLMs is substantially higher in many lower-resource
languages and for countries with a lower Human Development Index (HDI). We find that existing mitigation strategies provide uneven protection: input safety classifiers exhibit cross-lingual gaps, and
retrieval-augmented fact-checking remains inconsistent across regions due to unequal information availability. We release GlobalLies for research purposes, aiming to support the development of mitigation strategies to reduce the spread of global misinformation: https://github.com/zohaib-khan5040/globallies
Read the full abstract ▾
All authors Zohaib Khan, Mustafa Dogan, Ifeoma Okoh, Pouya Sadeghi, Siddhartha Shrestha, Sergius Justus Nyah, Mahmoud O. Mokhiamar, Michael J. Ryan, Tarek Naous
Computation and Language
CCD-CBT: Multi-Agent Therapeutic Interaction for CBT Guided by Cognitive Conceptualization Diagram
Chang Liu, Changsheng Ma, Yongfeng Tao et al. (+2 more)
Large
language models show potential for scalable mental-health support by simulating Cognitive Behavioral Therapy (CBT) counselors. However, existing methods often rely on static cognitive profiles and omniscient single-
agent simulation, failing to capture the dynamic, information-asymmetric nature of real therapy. We introduce CCD-CBT, a multi-
agent framework that shifts CBT simulation along two axes: 1) from a static to a dynamically reconstructed Cognitive Conceptualization Diagram (CCD), updated by a dedicated Control
Agent, and 2) from omniscient to information-asymmetric interaction, where the Therapist
Agent must reason from inferred client states. We release CCDCHAT, a synthetic multi-turn CBT
dataset generated under this framework. Evaluations with clinical scales and expert therapists show that models fine-tuned on CCDCHAT outperform strong baselines in both counseling fidelity and positive-affect enhancement, with ablations confirming the necessity of dynamic CCD guidance and asymmetric
agent design. Our work offers a new paradigm for building theory-grounded, clinically-plausible conversational
agents.
Read the full abstract ▾
All authors Chang Liu, Changsheng Ma, Yongfeng Tao, Bin Hu, Minqiang Yang
Computation and Language
The Illusion of Stochasticity in LLMs
Xiangming Gu, Soham De, Michalis Titsias et al. (+3 more)
In this work, we demonstrate that reliable
stochastic sampling is a fundamental yet unfulfilled requirement for Large
Language Models (LLMs) operating as
agents. Agentic systems are frequently required to sample from distributions, often inferred from observed data, a process which needs to be emulated by the LLM. This leads to a distinct failure point: while standard RL
agents rely on external sampling mechanisms, LLMs fail to map their internal probability estimates to their
stochastic outputs. Through rigorous empirical analysis across multiple model families, model sizes, prompting styles, and distributions, we demonstrate the extent of this failure. Crucially, we show that while powerful frontier models can convert provided random seeds to target distributions, their ability to sample directly from specific distributions is fundamentally flawed.
Read the full abstract ▾
All authors Xiangming Gu, Soham De, Michalis Titsias, Larisa Markeeva, Petar Veličković, Razvan Pascanu
Computation and Language
Does a Global Perspective Help Prune Sparse MoEs Elegantly?
Zeliang Zhang, Nikhil Ghosh, Jiani Liu et al. (+2 more)
Empirical scaling laws for
language models have encouraged the development of ever-larger LLMs, despite their growing computational and
memory costs. Sparse Mixture-of-Experts (MoEs) offer a promising alternative by activating only a subset of experts per forward pass, improving efficiency without sacrificing performance. However, the large number of expert parameters still leads to substantial
memory consumption. Existing
pruning methods typically allocate budgets uniformly across layers, overlooking the heterogeneous redundancy that arises in sparse MoEs. We propose GRAPE (Global Redundancy-Aware
Pruning of Experts, a global
pruning strategy that dynamically allocates
pruning budgets based on cross-layer redundancy. Experiments on Mixtral-8x7B, Mixtral-8x22B, DeepSeek-MoE, Qwen-MoE, and GPT-OSS show that, under the same
pruning budget, GRAPE consistently achieves the best average performance. On the three main models reported in the paper, it improves average accuracy over the strongest local baseline by 1.40% on average across
pruning settings, with gains of up to 2.45%.
Read the full abstract ▾
All authors Zeliang Zhang, Nikhil Ghosh, Jiani Liu, Bin Yu, Xiaodong Liu