English
Related papers

Related papers: Ulterior Motives: Detecting Misaligned Reasoning i…

200 papers

Reasoning with a chain-of-thought (CoT) enables Large Language Models (LLMs) to solve complex tasks but incurs significant inference costs due to the generation of long rationales. We propose Thinking States, a method that performs…

Computation and Language · Computer Science 2026-02-10 Ido Amos , Avi Caciularu , Mor Geva , Amir Globerson , Jonathan Herzig , Lior Shani , Idan Szpektor

Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other hand, COT prompting also poses new vulnerabilities in the…

Cryptography and Security · Computer Science 2024-01-24 Zhen Xiang , Fengqing Jiang , Zidi Xiong , Bhaskar Ramasubramanian , Radha Poovendran , Bo Li

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

Multimodal LLMs (MLLMs) with a great ability of text and image understanding have received great attention. To achieve better reasoning with MLLMs, Chain-of-Thought (CoT) reasoning has been widely explored, which further promotes MLLMs'…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Zefeng Wang , Zhen Han , Shuo Chen , Fan Xue , Zifeng Ding , Xun Xiao , Volker Tresp , Philip Torr , Jindong Gu

The chain-of-thought (CoT) paradigm uses the elicitation of step-by-step rationales as a proxy for reasoning, gradually refining the model's latent representation of a solution. However, it remains unclear just how early a Large Language…

Computation and Language · Computer Science 2025-11-20 Joey David

Chain of thought (CoT) elicits reasoning in large language models by explicitly generating intermediate tokens. In contrast, latent thought reasoning operates directly in the continuous latent space, enabling computation beyond discrete…

Artificial Intelligence · Computer Science 2026-05-13 Kevin Xu , Issei Sato

Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning steps. Providing these steps for prompting demonstrations is called chain-of-thought (CoT) prompting. CoT prompting has two major paradigms. One…

Computation and Language · Computer Science 2022-10-10 Zhuosheng Zhang , Aston Zhang , Mu Li , Alex Smola

Recent advancements in large language models have showcased their remarkable generalizability across various domains. However, their reasoning abilities still have significant room for improvement, especially when confronted with scenarios…

Computation and Language · Computer Science 2024-03-27 Xufeng Zhao , Mengdi Li , Wenhao Lu , Cornelius Weber , Jae Hee Lee , Kun Chu , Stefan Wermter

Chain-of-thought (CoT) monitoring is one of the most promising tools we have for detecting model misbehavior, but its effectiveness depends on models faithfully externalizing their reasoning. Motivated by this vulnerability, we study…

Machine Learning · Computer Science 2026-05-18 Reilly Haskins , Bilal Chughtai , Joshua Engels

While chain-of-thought (CoT) monitoring is an appealing AI safety defense, recent work on "unfaithfulness" has cast doubt on its reliability. These findings highlight an important failure mode, particularly when CoT acts as a post-hoc…

Artificial Intelligence · Computer Science 2025-07-08 Scott Emmons , Erik Jenner , David K. Elson , Rif A. Saurous , Senthooran Rajamanoharan , Heng Chen , Irhum Shafkat , Rohin Shah

Despite superior reasoning prowess demonstrated by Large Language Models (LLMs) with Chain-of-Thought (CoT) prompting, a lack of understanding prevails around the internal mechanisms of the models that facilitate CoT generation. This work…

Computation and Language · Computer Science 2024-05-07 Subhabrata Dutta , Joykirat Singh , Soumen Chakrabarti , Tanmoy Chakraborty

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

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

Large language models (LLMs) are increasingly being applied to clinical care, a domain where both accuracy and transparent reasoning are critical for safe and trustworthy deployment. Chain-of-thought (CoT) prompting, which elicits…

Computation and Language · Computer Science 2025-12-09 Jiageng Wu , Kevin Xie , Bowen Gu , Nils Krüger , Kueiyu Joshua Lin , Jie Yang

Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems, but remains constrained by the computational cost and reasoning path collapse when grounded in discrete token spaces. Recent latent reasoning…

Artificial Intelligence · Computer Science 2026-02-05 Jiecong Wang , Hao Peng , Chunyang Liu

Chain of Thought (CoT) is significant in improving the reasoning abilities of large language models (LLMs). However, the correlation between the effectiveness of CoT and the length of reasoning steps in prompts remains largely unknown. To…

Computation and Language · Computer Science 2024-06-25 Mingyu Jin , Qinkai Yu , Dong Shu , Haiyan Zhao , Wenyue Hua , Yanda Meng , Yongfeng Zhang , Mengnan Du

Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require process reward models,…

Artificial Intelligence · Computer Science 2026-05-26 Jingchu Gai , Guanning Zeng , Christina Baek , Chen Wu , J. Zico Kolter , Andrej Risteski , Aditi Raghunathan

Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work focuses predominantly on content safety (i.e.,…

Artificial Intelligence · Computer Science 2026-05-07 Xunguang Wang , Yuguang Zhou , Qingyue Wang , Zongjie Li , Ruixuan Huang , Zhenlan Ji , Pingchuan Ma , Shuai Wang

Large Language Models (LLMs) often exhibit \textit{hallucinations}, generating factually incorrect or semantically irrelevant content in response to prompts. Chain-of-Thought (CoT) prompting can mitigate hallucinations by encouraging…

Computation and Language · Computer Science 2025-09-17 Jiahao Cheng , Tiancheng Su , Jia Yuan , Guoxiu He , Jiawei Liu , Xinqi Tao , Jingwen Xie , Huaxia Li

Chain of thought (CoT) fine-tuning aims to endow large language models (LLMs) with reasoning capabilities by training them on curated reasoning traces. It leverages both supervised and reinforced fine-tuning to cultivate human-like…

Computation and Language · Computer Science 2026-03-24 Xiaoshu Chen , Sihang Zhou , Ke Liang , Duanyang Yuan , Haoyuan Chen , Xiaoyu Sun , Lingyuan Meng , Xinwang Liu