English
Related papers

Related papers: Ulterior Motives: Detecting Misaligned Reasoning i…

200 papers

Chain-of-Thought (CoT) reasoning is a critical capability for large language models (LLMs), enabling them to tackle com- plex multi-step tasks. While base LLMs, pre-trained on general text corpora, often struggle with reasoning due to a…

Computation and Language · Computer Science 2025-11-25 Zijian Wang , Yanxiang Ma , Chang Xu

Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial…

Cryptography and Security · Computer Science 2026-01-29 Xianglin Yang , Gelei Deng , Jieming Shi , Tianwei Zhang , Jin Song Dong

Reasoning Large Language Models (RLLMs) have demonstrated impressive performance on complex tasks, largely due to the adoption of Long Chain-of-Thought (Long CoT) reasoning. However, they often exhibit overthinking -- performing unnecessary…

Computation and Language · Computer Science 2025-05-30 Keqin Peng , Liang Ding , Yuanxin Ouyang , Meng Fang , Dacheng Tao

Do language models make decisions under uncertainty like humans do, and what role does chain-of-thought (CoT) reasoning play in the underlying decision process? We introduce an active probabilistic reasoning task that cleanly separates…

Machine Learning · Computer Science 2026-02-10 Gonçalo Guiomar , Elia Torre , Pehuen Moure , Victoria Shavina , Mario Giulianelli , Shih-Chii Liu , Valerio Mante

Large language models can use chain-of-thought (CoT) to externalize reasoning, potentially enabling oversight of capable LLM agents. Prior work has shown that models struggle at two-hop question-answering without CoT. This capability is so…

Computation and Language · Computer Science 2025-11-25 Mikita Balesni , Tomek Korbak , Owain Evans

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

Large Language Models (LLMs) face significant accuracy degradation due to insufficient reasoning ability when dealing with complex and abstract tasks. Thought structures such as Chain of Thought (CoT) and Tree of Thought (ToT) focus on…

Computation and Language · Computer Science 2025-09-29 Fengxiao Tang , Yufeng Li , Zongzong Wu , Ming Zhao

Latent or continuous chain-of-thought methods replace explicit textual rationales with a number of internal latent steps, but these intermediate computations are difficult to evaluate beyond correlation-based probes. In this paper, we view…

Artificial Intelligence · Computer Science 2026-05-29 Zirui Li , Xuefeng Bai , Kehai Chen , Yizhi Li , Jian Yang , Chenghua Lin , Min Zhang

Chain-of-Thought (CoT) reasoning has proven effective in natural language tasks but remains underexplored in multimodal alignment. This study investigates its integration into 3D vision-language learning by embedding structured reasoning…

Computation and Language · Computer Science 2025-03-18 Yanjun Chen , Yirong Sun , Xinghao Chen , Jian Wang , Xiaoyu Shen , Wenjie Li , Wei Zhang

Chain-of-Thought (CoT) prompting and its variants have gained popularity as effective methods for solving multi-step reasoning problems using pretrained large language models (LLMs). In this work, we analyze CoT prompting from a statistical…

Artificial Intelligence · Computer Science 2024-08-29 Xinyang Hu , Fengzhuo Zhang , Siyu Chen , Zhuoran Yang

Stance detection aims to identify the attitude expressed in a document towards a given target. Techniques such as Chain-of-Thought (CoT) prompting have advanced this task, enhancing a model's reasoning capabilities through the derivation of…

Computation and Language · Computer Science 2023-09-08 Kairui Hu , Ming Yan , Joey Tianyi Zhou , Ivor W. Tsang , Wen Haw Chong , Yong Keong Yap

Chain of Thought (CoT) of multi-step benefits from the logical structure of the reasoning steps and task-specific actions, significantly enhancing the mathematical reasoning capabilities of large language models. As the prevalence of long…

Artificial Intelligence · Computer Science 2025-03-07 Wen Yang , Minpeng Liao , Kai Fan

Recent advances in test-time scaling have enabled Large Language Models (LLMs) to display sophisticated reasoning abilities via extended Chain-of-Thought (CoT) generation. Despite their potential, these Reasoning LLMs (RLMs) often…

Computation and Language · Computer Science 2025-05-21 Zhen Xiong , Yujun Cai , Zhecheng Li , Yiwei Wang

Chain-of-Thought (CoT) reasoning typically utilizes the discrete language space for thinking, which is inherently inefficient, as many generated tokens only enforce linguistic rules that are not required for reasoning. To bypass this,…

Computation and Language · Computer Science 2025-12-16 Enes Özeren , Matthias Aßenmacher

Reasoning Language Models (RLMs) have gained traction for their ability to perform complex, multi-step reasoning tasks through mechanisms such as Chain-of-Thought (CoT) prompting or fine-tuned reasoning traces. While these capabilities…

Computation and Language · Computer Science 2025-07-04 Riccardo Cantini , Nicola Gabriele , Alessio Orsino , Domenico Talia

In language reasoning, longer chains of thought consistently yield better performance, which naturally suggests that visual latent reasoning may likewise benefit from longer latent sequences. However, we discover a counterintuitive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Chenfeng Wang , Wei He , Xuhan Zhu , Chunpeng Zhou , Qizhen Li , Song Yan , Yufei Zheng , Chengjun Yu , Fan Lu , Wei Zhai , Yang Cao , Pengfei Yu , Zheng-Jun Zha

Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by decomposing complex problems into step-by-step solutions, improving performance on reasoning tasks. However, current CoT disclosure policies vary widely across…

Computers and Society · Computer Science 2025-03-20 Yihang Chen , Haikang Deng , Kaiqiao Han , Qingyue Zhao

Chain-of-Thought (CoT) explanations are widely used to interpret how language models solve complex problems, yet it remains unclear whether these step-by-step explanations reflect how the model actually reaches its answer, or merely…

Computation and Language · Computer Science 2026-02-13 Donald Ye , Max Loffgren , Om Kotadia , Linus Wong

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

Chain-of-thought (CoT) reasoning boosts large language models' (LLMs) performance on complex tasks but faces two key limitations: a lack of reliability when solely relying on LLM-generated reasoning chains and lower reasoning performance…

Computation and Language · Computer Science 2025-09-11 Feiyang Li , Peng Fang , Zhan Shi , Arijit Khan , Fang Wang , Weihao Wang , Xin Zhang , Yongjian Cui