English
Related papers

Related papers: Mapping Faithful Reasoning in Language Models

200 papers

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…

Machine Learning · Computer Science 2026-05-26 Jinghan Jia , Joe Benton , Eric Easley

Chain-of-thought (CoT) traces are increasingly used both to improve language model capability and to audit model behavior, implicitly assuming that the visible trace remains synchronized with the computation that determines the answer. We…

Artificial Intelligence · Computer Science 2026-05-13 Wenkai Li , Fan Yang , Ananya Hazarika , Shaunak A. Mehta , Koichi Onoue

Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT is a direct window into what the model is thinking. This…

Machine Learning · Computer Science 2025-12-02 Austin Meek , Eitan Sprejer , Iván Arcuschin , Austin J. Brockmeier , Steven Basart

While Chain-of-Thought (CoT) prompting boosts Language Models' (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect how the model arrives at the answer (aka. faithfulness). We…

Computation and Language · Computer Science 2023-09-22 Qing Lyu , Shreya Havaldar , Adam Stein , Li Zhang , Delip Rao , Eric Wong , Marianna Apidianaki , Chris Callison-Burch

Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments, yet its effectiveness depends on faithfulness (whether models accurately verbalize the factors that…

Computation and Language · Computer Science 2026-03-25 Richard J. Young

Recent work has demonstrated that Chain-of-Thought (CoT) often yields limited gains for soft-reasoning problems such as analytical and commonsense reasoning. CoT can also be unfaithful to a model's actual reasoning. We investigate the…

Artificial Intelligence · Computer Science 2025-08-28 Samuel Lewis-Lim , Xingwei Tan , Zhixue Zhao , Nikolaos Aletras

Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism. Yet behavioral gains under CoT do not imply that the model's internal computation causally depends on the emitted reasoning…

Machine Learning · Computer Science 2026-02-10 Anish Sathyanarayanan , Aditya Nagarsekar , Aarush Rathore

Chain-of-thought (CoT) supervision can substantially improve transformer performance, yet the mechanisms by which models learn to follow and benefit from CoT remain poorly understood. We investigate these learning dynamics through the lens…

Machine Learning · Computer Science 2025-10-31 Zihan Pengmei , Costas Mavromatis , Zhengyuan Shen , Yunyi Zhang , Vassilis N. Ioannidis , Huzefa Rangwala

Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes of the model. We present the first comprehensive study of…

Computation and Language · Computer Science 2025-11-04 Sriram Balasubramanian , Samyadeep Basu , Soheil Feizi

Chain of Thought (CoT) reasoning has demonstrated remarkable deep reasoning capabilities in both large language models (LLMs) and multimodal large language models (MLLMs). However, its reliability is often undermined by the accumulation of…

Artificial Intelligence · Computer Science 2025-11-26 Zijun Chen , Wenbo Hu , Richang Hong

Chain-of-thought (CoT) prompting boosts Large Language Models accuracy on multi-step tasks, yet whether the generated "thoughts" reflect the true internal reasoning process is unresolved. We present the first feature-level causal study of…

Computation and Language · Computer Science 2025-08-01 Xi Chen , Aske Plaat , Niki van Stein

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…

Computation and Language · Computer Science 2026-05-28 Pruthvinath Jeripity Venkata

Chain-of-Thought (CoT) prompting helps models think step by step. But naive CoT breaks down in visually grounded social tasks, where models must perceive, understand, and judge all at once; bridging perception with norm-grounded reasoning.…

Computation and Language · Computer Science 2026-04-21 Eunkyu Park , Wesley Hanwen Deng , Gunhee Kim , Motahhare Eslami , Maarten Sap

Large reasoning models (LRMs) increasingly rely on step-by-step Chain-of-Thought (CoT) reasoning to improve task performance, particularly in high-resource languages such as English. While recent work has examined final-answer accuracy in…

Computation and Language · Computer Science 2025-10-13 Raoyuan Zhao , Yihong Liu , Hinrich Schütze , Michael A. Hedderich

Chain-of-thought (CoT) prompting is a de-facto standard technique to elicit reasoning-like responses from large language models (LLMs), allowing them to spell out individual steps before giving a final answer. While the resemblance to…

Artificial Intelligence · Computer Science 2026-02-26 Gregor Bachmann , Yichen Jiang , Seyed Mohsen Moosavi Dezfooli , Moin Nabi

Chain-of-thought (CoT) prompting has been widely adopted to enhance the reasoning capabilities of large language models (LLMs). However, the effectiveness of CoT reasoning is inconsistent across tasks with different reasoning types. This…

Machine Learning · Computer Science 2025-06-17 Yue Wan , Xiaowei Jia , Xiang Lorraine Li

While Chain-of-Thought (CoT) prompting enhances the reasoning capabilities of large language models, the faithfulness of the generated rationales remains an open problem for model interpretability. We propose a novel theoretical lens for…

Artificial Intelligence · Computer Science 2025-10-02 Elija Perrier

Chain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model's CoT to try to understand its intentions and reasoning processes. However, the effectiveness of such monitoring hinges on CoTs faithfully…

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…

Artificial Intelligence · Computer Science 2026-05-27 Hao Yang , Qinghua Zhao , Lei Li , Lingyi Meng , Mengda Yu

Recent impressive results from large reasoning models have been interpreted as a triumph of Chain of Thought (CoT), and especially of the process of training on CoTs sampled from base LLMs in order to help find new reasoning patterns. While…

Machine Learning · Computer Science 2026-05-27 Karthik Valmeekam , Vardhan Palod , Kaya Stechly , Atharva Gundawar , Subbarao Kambhampati
‹ Prev 1 2 3 10 Next ›