English
Related papers

Related papers: Reasoning Models Will Sometimes Lie About Their Re…

200 papers

Large Reasoning Models (LRMs) have significantly enhanced their capabilities in complex problem-solving by introducing a thinking draft that enables multi-path Chain-of-Thought explorations before producing final answers. Ensuring the…

Artificial Intelligence · Computer Science 2025-05-30 Zidi Xiong , Shan Chen , Zhenting Qi , Himabindu Lakkaraju

Large Reasoning Models (LRMs) exhibit strong performance, yet often produce rationales that sound plausible but fail to reflect their true decision process, undermining reliability and trust. We introduce a formal framework for reasoning…

Artificial Intelligence · Computer Science 2026-02-24 Yunseok Han , Yejoon Lee , Jaeyoung Do

Chain-of-thought (CoT) reasoning generated by large language models (LLMs) is often unfaithful: intermediate steps can be logically inconsistent or fail to reflect the causal relationship leading to the final answer. Despite extensive…

Machine Learning · Computer Science 2026-02-03 Fuxin Wang , Amr Alazali , Yiqiao Zhong

Do large language models (LLMs) display rational reasoning? LLMs have been shown to contain human biases due to the data they have been trained on; whether this is reflected in rational reasoning remains less clear. In this paper, we answer…

Computation and Language · Computer Science 2024-02-16 Olivia Macmillan-Scott , Mirco Musolesi

Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…

Computation and Language · Computer Science 2025-07-16 Pedro Ferreira , Wilker Aziz , Ivan Titov

Despite their strengths, large language models (LLMs) often fail to communicate their confidence accurately, making it difficult to assess when they might be wrong and limiting their reliability. In this work, we demonstrate that reasoning…

Artificial Intelligence · Computer Science 2025-10-23 Dongkeun Yoon , Seungone Kim , Sohee Yang , Sunkyoung Kim , Soyeon Kim , Yongil Kim , Eunbi Choi , Yireun Kim , Minjoon Seo

This study investigates the internal information flow of large language models (LLMs) while performing chain-of-thought (CoT) style reasoning. Specifically, with a particular interest in the faithfulness of the CoT explanation to LLMs'…

Computation and Language · Computer Science 2026-03-20 Keito Kudo , Yoichi Aoki , Tatsuki Kuribayashi , Shusaku Sone , Masaya Taniguchi , Ana Brassard , Keisuke Sakaguchi , Kentaro Inui

Large language models (LLMs) often improve their performance in downstream tasks when they generate Chain of Thought reasoning text before producing an answer. We investigate how LLMs recover from errors in Chain of Thought. Through…

Artificial Intelligence · Computer Science 2024-09-04 Evelyn Yee , Alice Li , Chenyu Tang , Yeon Ho Jung , Ramamohan Paturi , Leon Bergen

Can large language models (LLMs) express their uncertainty in situations where they lack sufficient parametric knowledge to generate reasonable responses? This work aims to systematically investigate LLMs' behaviors in such situations,…

Computation and Language · Computer Science 2024-02-19 Genglin Liu , Xingyao Wang , Lifan Yuan , Yangyi Chen , Hao Peng

Large language models (LLMs) encode parametric knowledge about world facts and have shown remarkable performance in knowledge-driven NLP tasks. However, their reliance on parametric knowledge may cause them to overlook contextual cues,…

Computation and Language · Computer Science 2023-10-24 Wenxuan Zhou , Sheng Zhang , Hoifung Poon , Muhao Chen

Large language models (LLMs) have been found to produce hallucinations when the question exceeds their internal knowledge boundaries. A reliable model should have a clear perception of its knowledge boundaries, providing correct answers…

Computation and Language · Computer Science 2024-08-20 Shiyu Ni , Keping Bi , Lulu Yu , Jiafeng Guo

As large language models (LLMs) perform more difficult tasks, it becomes harder to verify the correctness and safety of their behavior. One approach to help with this issue is to prompt LLMs to externalize their reasoning, e.g., by having…

Large language models (LLMs) can produce chains of thought (CoT) that do not accurately reflect the actual factors driving their answers. In multiple-choice settings with an injected hint favoring a particular option, models may shift their…

Machine Learning · Computer Science 2026-03-19 Parsa Mirtaheri , Mikhail Belkin

In day-to-day communication, people often approximate the truth - for example, rounding the time or omitting details - in order to be maximally helpful to the listener. How do large language models (LLMs) handle such nuanced trade-offs? To…

Computation and Language · Computer Science 2024-02-14 Ryan Liu , Theodore R. Sumers , Ishita Dasgupta , Thomas L. Griffiths

Large Language Models (LLMs) tend to be unreliable in the factuality of their answers. To address this problem, NLP researchers have proposed a range of techniques to estimate LLM's confidence over facts. However, due to the lack of a…

Computation and Language · Computer Science 2024-11-28 Matéo Mahaut , Laura Aina , Paula Czarnowska , Momchil Hardalov , Thomas Müller , Lluís Màrquez

Large Language Models (LLMs) are effective at deceiving, when prompted to do so. But under what conditions do they deceive spontaneously? Models that demonstrate better performance on reasoning tasks are also better at prompted deception.…

Computation and Language · Computer Science 2025-04-02 Samuel M. Taylor , Benjamin K. Bergen

Chain-of-Thought (CoT) monitoring has emerged as a compelling method for detecting harmful behaviors such as reward hacking for reasoning models, under the assumption that models' reasoning processes are informative of such behaviors. In…

Machine Learning · Computer Science 2026-03-10 Nikolaus Howe , Micah Carroll

Large Language Models (LLMs) have shown remarkable progress across domains, yet their ability to perform inductive reasoning - inferring latent rules from sparse examples - remains limited. It is often assumed that chain-of-thought (CoT)…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Haibo Jin , Peiyan Zhang , Man Luo , Haohan Wang

We study how well large language models (LLMs) explain their generations through rationales -- a set of tokens extracted from the input text that reflect the decision-making process of LLMs. Specifically, we systematically study rationales…

Computation and Language · Computer Science 2024-10-23 Mohsen Fayyaz , Fan Yin , Jiao Sun , Nanyun Peng

When using large language models (LLMs) in high-stakes applications, we need to know when we can trust their predictions. Some works argue that prompting high-performance LLMs is sufficient to produce calibrated uncertainties, while others…