Search: chain of thought

520 papers found.

• Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded Reasoning

  Julian Schulz · 28 September 2026 · Digital and Cyber Forensics

  Chain-of-thought (CoT) monitoring is a promising safety technique for reasoning models, enabling detection of problematic reasoning before models act. A key concern is encoded reasoning, where models hide their true reasoning in ways that monitors and humans cannot interpret. Optimization pressure f…

• LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning

  Qingjing Chen, Junkai Zhang, Shaochun Wang, Jiahao Ding, Siyuan Zheng, Yukun Yan, Zhi Zheng, Antonino Rotolo, Yun Liu, Weixing Shen · 24 September 2026 · Artificial Intelligence in Law

  Large language models are increasingly applied to high-risk domains such as law, yet complex legal reasoning remains limited by two structural challenges. First, existing RAG and GraphRAG methods emphasize lexical or semantic similarity while overlooking normative relations among legal provisions. S…

• What Does Chain-of-Thought Entropy Measure? A Channel Audit of Scaffolding, Routing, and Content

  Marios Papamichalis, Regina Ruane · 23 September 2026 · Large Language Models

  Entropy over chain-of-thought tokens decides which tokens receive the policy gradient, which get pruned, and whether a run has collapsed, yet each such statistic reads a next-token distribution mixing three choices: whether to emit connective scaffolding, which connective, and what the substantive c…

• Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models

  Xiaoyu Luo, Tao Ren, Wenrui Yu, Xiao Li, Qiongxiu Li, Johannes Bjerva · 23 September 2026 · Semantic Web and Ontologies

  The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden. By registering a simple custom tool through a standard API feature, we induce frontier models to externaliz…

• From Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought

  Renee Jia, Di Mu · 23 September 2026 · Large Language Models

  Chain-of-thought (CoT) monitoring is only meaningful if written reasoning causally constrains the answer. We introduce continuation-based causal testing, an ablation-patch intervention that perturbs one reasoning step, truncates the chain, and forces the model to continue from the corrupted prefix. …

• CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model

  Ziming Xu, Shuang Liang, Ruobing Han, Ziqiao Xi, Mingxing Rao, Kun Zhou, Zijun Zhang, Yuchen Yan, Yufan Wei, Junbo Huang, Yifei Shao, Fang Nan, Biwei Huang · 22 September 2026 · Multimodal Machine Learning Applications

  Embodied world models learn to predict future physical dynamics from visual observations and control signals, where physical knowledge is implicitly entangled within latent representations. We introduce CausalWM, a 16B embodied world model that performs explicit causal chain-of-thought reasoning bef…

• From Concept Alignment to Causal Grounding: An Intervention Test of Chain-of-Thought Faithfulness

  Qianli Wang, Yilong Wang, Dennis Wei, Jingyi Sun, Simon Ostermann, Pepa Atanasova, Nils Feldhus · 22 September 2026 · Religion, Spirituality, and Psychology

  Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through input--output behavior or input attributions, leaving internal computation largely underexplored. We instead cast faithfulness as internal concept groundi…

• COT-TTS: Audio Context-Aware Text-to-Speech with Chain-of-Thought Reasoning

  Weizhen Bian, Sitong Cheng, Rongxiu Zhong, Jiahao Pan, Liumeng Xue, Boyi Kang, Shilei Zhang, Jinglei Liu, Yue Wang, Junlan Feng, Bei Liu, Wei Xue · 22 September 2026 · Speech Recognition and Synthesis

  Recently, text-to-speech systems have made significant progress in speech expressiveness and controllability. However, the speaking style of generated speech typically relies on clear user-specified instructions. In natural conversations, speaking style should be naturally inferred from the precedin…

• Quantifying Hidden Salt for Precision Healthcare: Sodium Assessment via Joint-Factor Retrieval and Chain-of-Thought Inference

  Mingyu Huang, Weiqing Min, Yuehui Fang, Yuna He, Shuqiang Jiang · 22 September 2026 · Nutrition, Genetics, and Disease

  Precision healthcare, particularly for conditions like hypertension and cardiovascular disease, necessitates monitoring of dietary sodium intake. However, tracking this is hindered by the prevalence of hidden salt in cooking, such as sodium in soy sauce and ketchup. While recipes offer a valuable da…

• Chain-of-Thought Entropy as a Reliability Signal: A Preregistered Reproduction

  Theodore O. Cochran · 18 September 2026 · Large Language Models

  This empirical study is an independent reproduction of the dissociation Zhao reported in 2026. The shape of a large language model's chain-of-thought entropy trajectory predicts whether the final answer is correct, while the magnitude of its total entropy drop does not. The dissociation merits repro…

• Faithful yet Collusive: Why Chain-of-Thought Monitoring Cannot Detect Collusion in LLM Pricing Agents under Oligopolistic Competition

  Dohun Lee, Hyunwoo Park · 17 September 2026 · Auction Theory and Applications

  Large language models (LLM) deployed as autonomous pricing agents may sustain supracompetitive prices through tacit coordination. We develop a causal graph divergence framework that separately measures structural faithfulness and intent faithfulness of LLM pricing agents in Bertrand competition. Acr…

• Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan Injection

  Keertana Chidambaram, Andrew Ilyas, Vasilis Syrgkanis · 15 September 2026 · Security and Verification in Computing

  Chain-of-thought (CoT) monitoring is a safety strategy where the reasoning of a large language model "actor" is inspected by a "monitor" (often another language model) for signs of unsafe planning, deception, or misalignment. We find that planting harmful but benign-sounding reasoning in the actor's…

• Beyond Generation and Accuracy: Diagnosing and Enhancing Visual Chain-of-Thought for Geometry Problem Solving

  Zhitong Dong, Jicai Pan, Yingguo Gao, Jingting Ding, Hao Chen, Jinjie Gu · 14 September 2026 · Multimodal Machine Learning Applications

  While multimodal reasoning has advanced rapidly, solving complex geometry problems critically hinges on active visual assistance, such as constructing auxiliary lines, spurring the rise of Visual Chain-of-Thought (VCoT). However, existing evaluations typically assess visual generation quality and fi…

• CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision Making

  Cagri Temel · 10 September 2026 · Social Robot Interaction and HRI

  Chain-of-Thought (CoT) prompting enables LLMs to perform explicit, step-by-step reasoning, creating opportunities for sophisticated autonomous robots. However, recent research reveals that reasoning models verbalize their actual decision processes only 25-39% of the time, with faithfulness degrading…

• Structural Process Supervision for Latent Chain-of-Thought Reasoning

  Yiqi Li, Xu Chen, Chen Ju, Jiangchao Yao, Zhaoyang Li, Jinsong Lan, Xiaoyong Zhu, Bo Zheng, Yu Wang · 10 September 2026 · Semantic Web and Ontologies

  Latent reasoning approaches enhance token-level efficiency and robustness by replacing verbose, explicit chain-of-thought (CoT) tokens with compact continuous-space embeddings. However, existing methods lack direct process supervision over these latent embeddings, which often leads to representation…

• Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models

  Bayar Menzat, Maximilian S\"uss, Ruizhi Wang, Benno Steinegger, Thomas Lukasiewicz, Oana-Maria Camburu · 9 September 2026 · Multimodal Machine Learning Applications

  Chain-of-thought (CoT) may often look plausible, yet it may not faithfully reflect the model's decision-making process. While methods for measuring the faithfulness of CoTs for textual inputs have been increasingly introduced, using these methods for visual inputs is not straightforward. In this wor…

• Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs

  Seogyeong Jeong, Jaehui Hwang, Dongyoon Han, Geonmo Gu, Alice Oh, Taekyung Kim · 7 September 2026 · Semantic Web and Ontologies

  Reasoning in large language models unfolds through diverse functional operations, such as problem formulation, goal decomposition, and deduction. Although these operations are explicitly distinguished in text, little is known about how they are geometrically organized in representation spaces. To th…

• MCPO: Modality-Contrastive Preference Optimization for Multimodal Chain-of-Thought Compression

  Guangheng Yang, Zhenliang Ni, Zhenkai Wu, Han Shu, Juan Feng, Wenming Yang, Jie Hu · 7 September 2026 · Multimodal Machine Learning Applications

  Recently, multimodal large-scale reasoning models have demonstrated remarkable capabilities in solving complex tasks through long Chains-of-Thought (M-CoT). However, excessively long reasoning trajectories incur substantial computational costs and significant KV-cache pressure. Existing CoT compress…

• Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning

  Kevin Du, Alexander Hoyle, Laura Ruis, Acyr Locatelli · 4 September 2026 · Large Language Models

  Reasoning traces from chain-of-thought models appear to offer a legible window into how a model arrives at its answer. A growing body of work treats them as such, using LLM judges to diagnose errors, evaluate faithfulness, and provide step-level supervision via process reward models and generative c…

• Dependency-Aware Chain-of-Thought Compression for Financial Reasoning

  Wenjun Wu, Lei Fu, Kejian Tong, Tao Ning, Sichen Zhao · 2 September 2026 · Semantic Web and Ontologies

  Chain of thought prompting improves complex reasoning, but its long intermediate traces create substantial inference cost and hinder practical deployment in financial settings. We present a Hierarchical Semantic Distillation Network, HSDN, for compressing reasoning chains while preserving answer acc…

• SCAFFOLD: A Large-Scale Structured Dataset of Computer Science Research Figures with Diagram QA and Chain-of-Thought Reasoning Traces

  Ranjit Raut, Aarav Subedi, Sagun Rai, Sudan Jha · 2 September 2026 · Semantic Web and Ontologies

  Computer science papers rely heavily on diagrams: architecture drawings, system flowcharts, and pipeline schematics that often carry more information than the text around them. There is currently no public dataset that pairs this specific kind of figure with captions, context, questions, answers, an…

• Beyond Polarization: The Generative Constraint of Chain-of-Thought in Pointwise Reranking

  Xiaoyang Chen, Jie Liu, Haijin Liang, Haibo Shi, Jin Ma, Ben He, Yingfei Sun, Dezhi Ye · 1 September 2026 · Information Retrieval and Search Behavior

  In pointwise document reranking, Chain-of-Thought models typically underperform direct scoring models. While existing diagnostics attribute this to inferior classification, score polarization, or calibration breakdown, whether targeted training can bridge this gap remains unclear. Our empirical stud…

• Detecting Hidden Chain-of-Thought in Large Language Models with Linguistic, Behavioral, and Mechanistic Indicators

  Armaan Singh, Ryan Trinh Le, Jasmine Kaur, Abdullah Sultan, Edward Lue Chee Lip, Kiran Nijjer, Adnan Ahmed, Vasu Sharma · 1 September 2026 · Large Language Models

  Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete patterns. We propose the Hidden CoT Detection Score (HCDS), a comparative behavioral and mechanistic signal measuring whether neutral-prompt behavior …

• MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for Chain-of-Thought Distillation

  Yangsong Lan, Renkai Hu, HongKai Zheng, Bo Zhang, Renzhi Wang, Hongliang Dai, Piji Li · 1 September 2026 · Large Language Models

  Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning. However, distilling such trajectories into smaller student models remains challenging: direct Long CoT supervision often provides limited gains and c…

• Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered

  Aryo Pradipta Gema, Neel Rajani, Rohit Saxena, Wai-Chung Kwan, Pasquale Minervini · 1 September 2026 · Large Language Models

  Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness tests often place explicit bias cues in the user message, while agents may encounter preferences through tool returns or raw artifacts. We introduce F…