English
Related papers

Related papers: Thought Purity: A Defense Framework For Chain-of-T…

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) 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

Recent studies have discovered that Chain-of-Thought prompting (CoT) can dramatically improve the performance of Large Language Models (LLMs), particularly when dealing with complex tasks involving mathematics or reasoning. Despite the…

Machine Learning · Computer Science 2023-12-27 Guhao Feng , Bohang Zhang , Yuntian Gu , Haotian Ye , Di He , Liwei Wang

Large Reasoning Models (LRMs) achieve promising performance but compromise token efficiency due to verbose reasoning processes. Unconscious Thought Theory (UTT) posits that complex problems can be solved more efficiently through…

Computation and Language · Computer Science 2025-05-27 Ruihan Gong , Yue Liu , Wenjie Qu , Mingzhe Du , Yufei He , Yingwei Ma , Yulin Chen , Xiang Liu , Yi Wen , Xinfeng Li , Ruidong Wang , Xinzhong Zhu , Bryan Hooi , Jiaheng Zhang

Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning. However, CoT is not always faithful to the model's final output, undermining its reliability as a monitoring…

Computation and Language · Computer Science 2026-05-19 Maciej Chrabąszcz , Aleksander Szymczyk , Marcin Sendera , Tomasz Trzciński , Sebastian Cygert

In information retrieval, large language models (LLMs) have demonstrated remarkable potential in text reranking tasks by leveraging their sophisticated natural language understanding and advanced reasoning capabilities. However,…

Information Retrieval · Computer Science 2025-09-22 Haowei Liu , Xuyang Wu , Guohao Sun , Zhiqiang Tao , Yi Fang

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their explicit chain-of-thought (CoT) mechanism introduces new…

Artificial Intelligence · Computer Science 2026-05-26 Jianan Li , Simeng Qin , Xiaojun Jia , Lionel Z. Wang , Tianhang Zheng , Xiaoshuang Jia , Yang Liu , Xiaochun Cao

Chain-of-Thought (CoT) prompting has emerged as a foundational technique for eliciting reasoning from Large Language Models (LLMs), yet the robustness of this approach to corruptions in intermediate reasoning steps remains poorly…

Computation and Language · Computer Science 2026-04-20 Ashwath Vaithinathan Aravindan , Mayank Kejriwal

Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about safety alignment and are easily biased when a flawed premise…

Large language models (LLMs) excel at complex reasoning but can still exhibit harmful behaviors. Current alignment strategies typically embed safety into model weights, making these controls implicit, static, and difficult to modify. This…

Computation and Language · Computer Science 2025-10-15 Xuanming Zhang , Yuxuan Chen , Samuel Yeh , Sharon Li

Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computational efficiency as a new attack surface. In this paper, we…

Cryptography and Security · Computer Science 2025-11-17 Shuaitong Liu , Renjue Li , Lijia Yu , Lijun Zhang , Zhiming Liu , Gaojie Jin

Although Large Language Models (LLMs) have evolved from text generators into the cognitive core of modern AI systems, their inherent lack of authorization awareness exposes these systems to catastrophic risks, ranging from unintentional…

Artificial Intelligence · Computer Science 2026-04-06 Yang Li , Yule Liu , Xinlei He , Youjian Zhao , Qi Li , Ke Xu

Chain-of-Thought (CoT) prompting improves LLM reasoning but can increase privacy risk by resurfacing personally identifiable information (PII) from the prompt into reasoning traces and outputs, even under policies that instruct the model…

Computation and Language · Computer Science 2026-03-09 Patrick Ahrend , Tobias Eder , Xiyang Yang , Zhiyi Pan , Georg Groh

Explanations are often promoted as tools for transparency, but they can also foster confirmation bias; users may assume reasoning is correct whenever outputs appear acceptable. We study this double-edged role of Chain-of-Thought (CoT)…

Computation and Language · Computer Science 2025-11-20 Eunkyu Park , Wesley Hanwen Deng , Vasudha Varadarajan , Mingxi Yan , Gunhee Kim , Maarten Sap , Motahhare Eslami

We develop a learning-theoretic framework for understanding Chain of Thought (CoT). We model CoT as the interaction between an answer map and a chain rule that generates intermediate questions autoregressively, and define the reasoning risk…

Machine Learning · Computer Science 2026-05-21 Yue Zhang , Zhiyi Dong , Tommaso Cesari , Yongyi Mao

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a…

Machine Learning · Computer Science 2025-10-21 Mohan Zhang , Yihua Zhang , Jinghan Jia , Zhangyang Wang , Sijia Liu , Tianlong Chen

Recent progress in large reasoning models for challenging mathematical reasoning has been driven by reinforcement learning (RL). Incorporating long chain-of-thought (CoT) data during mid-training has also been shown to substantially improve…

Artificial Intelligence · Computer Science 2026-02-12 Xuemiao Zhang , Can Ren , Chengying Tu , Rongxiang Weng , Shuo Wang , Hongfei Yan , Jingang Wang , Xunliang Cai

Recent Vision-Language-Action (VLA) models increasingly adopt chain-of-thought (CoT) reasoning, generating a natural-language plan before decoding motor commands. This internal text channel between the reasoning module and the action…

Robotics · Computer Science 2026-03-16 Tuan Duong Trinh , Naveed Akhtar , Basim Azam

Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated with chain of thought prompting-a method of demonstrating solution…

Artificial Intelligence · Computer Science 2025-03-13 Kaya Stechly , Karthik Valmeekam , Subbarao Kambhampati

Large Reasoning Models (LRMs) face a distinct safety vulnerability: their internal reasoning chains may generate harmful content even when the final output appears benign. To address this overlooked risk, we first propose a novel attack…

Artificial Intelligence · Computer Science 2026-01-01 Jianhao Chen , Mayi Xu , Haoyang Chen , Xiaohu Li , Xiangyu Zhang , Jianjie Huang , Zheng Wang , Xiaochun Cao , Tieyun Qian