Search: chain of thought

520 papers found.

• COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models

  Arya Fayyazi, Mehdi Kamal, Massoud Pedram · 1 June 2026 · Ethics and Social Impacts of AI

  Large language models (LLMs) can reveal and amplify societal biases during chain-of-thought (CoT) generation. We present COFT (Chain of Fair Thought), a training-free decoding method that applies token-level fairness control at decode time, with distribution-free marginal validity guarantees (under …

• How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning

  Liyan Xu, Mo Yu, Fandong Meng, Jie Zhou · 29 May 2026 · Large Language Models

  Chain-of-thought (CoT) reasoning has become a central mechanism for eliciting multi-step reasoning in Large Language Models (LLMs). Yet recent evidence presents a tension: hidden states appear to already encode future reasoning before CoT fully unfolds, while explicit steps still remain crucial for …

• Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought

  Jiacheng Lu, Yiming Li, Tao Song, Weijian Wang, Wenjie Qu, Haibing Guan, Jiaheng Zhang · 29 May 2026 · Adversarial Robustness in Machine Learning

  Large Language Models with Chain-of-Thought reasoning capabilities represent valuable intellectual property, yet existing black-box watermarking methods often trade robustness for reasoning fidelity by perturbing final answers or relying on fragile trigger patterns. We propose BiCoT, a watermarking …

• Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models

  Xinyuan Cheng, Beiduo Chen, Philipp Mondorf, Barbara Plank · 28 May 2026 · Large Language Models

  Large reasoning models (LRMs) often generate extensive chain-of-thought (CoT) traces before producing a final answer. As explicit textual artifacts, these traces can be passed to other models to solve the same task, enabling cross-model reasoning transfer. Yet successful transfer alone does not reve…

• CIRF: Tokenizing Chain-of-Thoughts into Reusable Functional Units for Efficient Latent Reasoning in Large Language Models

  Yukyung Lee, Yumeng Shen, Jinhyeong Park, Hyein Yang, Jun-Hyung Park · 28 May 2026 · Large Language Models

  Implicit Chain-of-Thought (CoT) reduces the inference cost of large language models by internalizing the explicit rationales. However, existing approaches typically lack alignment with explicit rationales and adaptivity to example complexity. In this work, we propose CIRF (\textit{\underline{C}hain-…

• Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought

  Jiachen Zhao, Yiyou Sun, Weiyan Shi, Dawn Song · 28 May 2026 · Large Language Models

  Large language models can generate long chain-of-thought (CoT) reasoning, yet prior work suggests that CoT can be post-hoc rationalization rather than a faithful reflection of the computation through explicitly designed settings. In this work, we go further and propose a True Thinking Score (TTS) to…

• Transformers Provably Learn to Internalize Chain-of-Thought

  Yixiao Huang, Hanlin Zhu, Zixuan Wang, Jiantao Jiao, Stuart Russell, Somayeh Sojoudi, Song Mei · 28 May 2026 · Generative Adversarial Networks and Image Synthesis

  Chain-of-Thought (CoT) prompting substantially improves the sample efficiency of transformers, reducing the complexity of tasks like parity learning from exponential to polynomial in the input length. However, generating explicit reasoning steps at inference is computationally expensive. Implicit Ch…

• The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages

  Eric Onyame, Runtao Zhou, Kowshik Thopalli, Bhavya Kailkhura, Chirag Agarwal · 28 May 2026 · Deception detection and forensic psychology

  Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains largely unexplored beyond English and across diverse model families. We present the first large-scale evaluation of CoT mon…

• Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of-Thought Under Knowledge Conflict

  Pruthvinath Jeripity Venkata · 28 May 2026 · Memory Processes and Influences

  When a language model sees a document contradicting its training knowledge, it must choose: follow the document or trust itself. Prior work proved this choice depends on how well-known the fact is. We ask: does the model's chain-of-thought (CoT) reasoning faithfully report this mechanism? We introdu…

• Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought

  Yuchen Guo, Junli Gong, Hongmin Cai, Yiu-ming Cheung, Weifeng Su · 28 May 2026 · Multimodal Machine Learning Applications

  Recent segmentation models couple large language models (LLMs) with mask decoders to ground complex language expressions into masks, yet their instructions remain target-referential: they describe, constrain, or imply the region to be segmented. However, in real-world embodied interaction, human ins…

• Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation

  Zhaoyang Jiang, Xuanqi Peng, Fei Teng, Zhizhong Fu, Yunsoo Kim, Jiacong Mi, Zicheng Li, Honghan Wu · 28 May 2026 · Clinical Reasoning and Diagnostic Skills

  Chain-of-thought (CoT) distillation trains a smaller model to imitate a teacher's reasoning trace, but it is typically evaluated by final-answer metrics including accuracy. We ask whether gains in answer quality are accompanied by improvements in the trace. In medical QA, where short answer options …

• Chain Of Thought Compression: A Theoretical Analysis

  Juncai Li, Ru Li, Yuxiang Zhou, Boxiang Ma, Jeff Z. Pan · 27 May 2026 · Large Language Models

  Chain-of-Thought (CoT) has unlocked advanced reasoning abilities of Large Language Models (LLMs) with intermediate steps, yet incurs prohibitive computational costs due to generation of extra tokens. Recent studies empirically show that compressing reasoning steps into latent states, or implicit CoT…

• How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation

  Hao Yang, Qinghua Zhao, Lei Li, Lingyi Meng, Mengda Yu · 27 May 2026 · Scientific Research and Philosophical Inquiry

  Chain-of-Thought (CoT) prompting significantly enhances model reasoning, yet its internal mechanisms remain poorly understood. We analyze CoT's operational principles by reversely tracing information flow across decoding, projection, and activation phases. Our quantitative analysis suggests that CoT…

• GeoFaith: A Spatio-Temporal Dual View of Faithful Chain-of-Thought

  Weijiang Lv, Wentong Zhao, Jiayu Wang, Yuhao Wu, Jiaheng Wei, Xiaobo Xia · 27 May 2026 · Advanced Graph Neural Networks

  Chain-of-Thought (CoT) reasoning has advanced large language models (LLMs), but outcome-based supervision leads to pervasive post-hoc rationalization, producing plausible yet unfaithful reasoning chains. Most prior faithfulness assessment methods are either unscalable, expensive, or unreliable. We p…

• What Makes Chain-of-Thought Work at Probe Time? Local Co-occurrence Rather Than Global Derivation

  Xiang Wang, Wei Wei · 27 May 2026 · Large Language Models

  Chain-of-thought (CoT) prompting reliably improves language-model accuracy, but which properties of a rationale text drive the improvement is poorly understood. Prior work has largely studied generation-time behavior. We instead ask a probe-time question: given a fixed rationale in context, what in …

• Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal

  Kia-J\"ung Yang, Dominik Meier, Jiachen Zhao, Terry Ruas, Bela Gipp · 27 May 2026 · Adversarial Robustness in Machine Learning

  Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may complicate control mechanisms such as refusal. Unlike instruction-tuned LLMs, where refusal is mediated by a single directional subspace, refusal in larg…

• ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs

  Jiangyang Li, Cong Wan, Changjie Wu, Songlin Dong, Lingjun Zhang, Linzhe Shi, Xu Wang, Zhiheng Ma, Hang Zhang, Mu Xu, Yihong Gong · 26 May 2026 · Multimodal Machine Learning Applications

  Reliable spatial reasoning remains a core bottleneck for vision-language models (VLMs). Existing mainstream training paradigms for spatial reasoning largely rely on outcome alignment or process imitation, lacking explicit constraints on the reasoning process, and therefore struggle to ensure genuine…

• Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning

  Jinghan Jia, Joe Benton, Eric Easley · 26 May 2026 · Adversarial Robustness in Machine Learning

  Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produces the final answer. However, models can rely on prompt-to-answer shortcuts that bypass the CoT, making the visible reasoning trace misleading even w…

• Chain-of-Thought Hijacking

  Jianli Zhao, Tingchen Fu, Rylan Schaeffer, Mrinank Sharma, Fazl Barez · 26 May 2026 · Explainable Artificial Intelligence (XAI)

  Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reasoning should lead to more robust safety behavior, we find evidence to the contrary: over-extended reasoning can instead be exploited to systematically w…

• Creative Quality Alignment: Expert Tacit Knowledge Transfer via Chain-of-Thought Fine-Tuning

  Bo Zou, Chao Xu · 26 May 2026 · Design Education and Practice

  This paper provides an empirical implementation of the creative quality metric proposed in Calibrated Surprise (Zou & Xu, 2026a). The question this paper addresses is: does this mathematical claim hold at the engineering level? To make the answer as general as possible, we deliberately choose the …

• Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program Optimization

  Mengfan Liu, Da Zheng, Junwei Su, Chuan Wu · 26 May 2026 · Machine Learning in Materials Science

  Despite the strong reasoning capabilities of large language models (LLMs), optimizing the execution efficiency of tensor programs remains challenging due to the need for precise, composable transformation decisions. Recent LLM-guided approaches frame tensor program optimization as an iterative decis…

• BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data

  Bo Zou, Chao Xu · 26 May 2026 · Large Language Models

  High-quality expert chain-of-thought (CoT) data is one of the core bottlenecks in large language model (LLM) post-training. Existing data production methods each have structural limitations: crowdsourced annotation lacks deep reasoning paths; expert solo writing is constrained by the "expert blind s…

• Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization

  Jingyi Sun, Qianli Wang, Pepa Atanasova, Nils Feldhus, Isabelle Augenstein · 26 May 2026 · Large Language Models

  Chain-of-Thought (CoT) faithfulness, i.e., whether CoTs genuinely reflect large language models' (LLM) underlying behavior, is typically evaluated under two disjoint paradigms: contextual faithfulness, measured by perturbing the input or CoT trace, and parametric faithfulness, assessed by intervenin…

• MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning

  Aritra Dutta, Somak Aditya · 26 May 2026 · Multimodal Machine Learning Applications

  Vision-language models (VLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex multimodal tasks, but their large parameter sizes make deployment expensive. Structured pruning offers a natural solution; however, existing methods fail to preserve CoT reasoning accuracy in VLMs. W…

• Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy

  Xu Shen, Zhen Tan, Song Wang, Pingjun Hong, Rui Miao, Xin Wang, Tianlong Chen · 26 May 2026 · Large Language Models

  Chain-of-thought (CoT) reasoning improves the problem-solving ability of large language models (LLMs), but generated reasoning traces may not faithfully reflect the model's actual decision process. Existing CoT unfaithfulness detectors mainly rely on external signals from generated rationales, such …