English
Related papers

Related papers: Safer Reasoning Traces: Measuring and Mitigating C…

200 papers

Large Reasoning Models (LRMs) improve performance, reliability, and interpretability by generating explicit chain-of-thought (CoT) reasoning, but this transparency introduces a serious privacy risk: intermediate reasoning often leaks…

Artificial Intelligence · Computer Science 2026-01-09 Arghyadeep Das , Sai Sreenivas Chintha , Rishiraj Girmal , Kinjal Pandey , Sharvi Endait

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

As Large Language Models (LLMs) evolve into personal assistants with access to sensitive user data, they face a critical privacy challenge: while prior work has addressed output-level privacy, recent findings reveal that LLMs often leak…

Cryptography and Security · Computer Science 2025-11-24 Shourya Batra , Pierce Tillman , Samarth Gaggar , Shashank Kesineni , Kevin Zhu , Sunishchal Dev , Ashwinee Panda , Vasu Sharma , Maheep Chaudhary

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

We study privacy leakage in the reasoning traces of large reasoning models used as personal agents. Unlike final outputs, reasoning traces are often assumed to be internal and safe. We challenge this assumption by showing that reasoning…

Computation and Language · Computer Science 2025-10-02 Tommaso Green , Martin Gubri , Haritz Puerto , Sangdoo Yun , Seong Joon Oh

Chain-of-thought (CoT) prompting is a common technique for improving the reasoning abilities of large language models (LLMs). However, extended reasoning is often unnecessary and substantially increases token usage. As such, a key question…

Computation and Language · Computer Science 2026-01-09 Samuel Lewis-Lim , Xingwei Tan , Zhixue Zhao , Nikolaos Aletras

Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs leaking Personally Identifiable Information (PII) has…

Machine Learning · Computer Science 2023-04-25 Nils Lukas , Ahmed Salem , Robert Sim , Shruti Tople , Lukas Wutschitz , Santiago Zanella-Béguelin

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

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

Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT…

Computation and Language · Computer Science 2023-12-12 Miles Turpin , Julian Michael , Ethan Perez , Samuel R. Bowman

Chain-of-Thought (CoT) prompting has been used to enhance the reasoning capability of LLMs. However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly under structured human evaluation.…

Cryptography and Security · Computer Science 2026-04-07 Jiling Zhou , Aisvarya Adeseye , Seppo Virtanen , Antti Hakkala , Jouni Isoaho

Large language models (LLMs) are increasingly deployed in socially sensitive settings despite substantial documentation that they encode gender biases. Chain-of-Thought (CoT) prompting has been proposed as a bias-mitigation approach.…

Computation and Language · Computer Science 2026-05-21 Edie Pearman , Sophia Osborne , Mira Kandlikar-Bloch , Mina Arzaghi , Florian Carichon , Golnoosh Farnadi

Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-training share the core objective: iteratively leveraging…

Computation and Language · Computer Science 2025-05-27 Zongqian Wu , Baoduo Xu , Ruochen Cui , Mengmeng Zhan , Xiaofeng Zhu , Lei Feng

Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to…

Cryptography and Security · Computer Science 2026-01-29 Harsh Chaudhari , Ethan Rathbun , Hanna Foerster , Jamie Hayes , Matthew Jagielski , Milad Nasr , Ilia Shumailov , Alina Oprea

This is the second in a series of short reports that seek to help business, education, and policy leaders understand the technical details of working with AI through rigorous testing. In this report, we investigate Chain-of-Thought (CoT)…

Computation and Language · Computer Science 2025-06-10 Lennart Meincke , Ethan Mollick , Lilach Mollick , Dan Shapiro

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) 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

Current Large Language Models (LLMs), especially Large Reasoning Models, can generate Chain-of-Thought (CoT) reasoning traces to illustrate how they produce final outputs, thereby facilitating trust calibration for users. However, these CoT…

Human-Computer Interaction · Computer Science 2026-04-07 Shiwei Chen , Niruthikka Sritharan , Xiaolin Wen , Chenxi Zhang , Xingbo Wang , Yong Wang

Chain-of-thought (CoT) reasoning is fundamental to modern LLM architectures and represents a critical intervention point for AI safety. However, CoT reasoning may exhibit failure modes that we note as pathologies, which prevent it from…

Artificial Intelligence · Computer Science 2026-02-17 Manqing Liu , David Williams-King , Ida Caspary , Linh Le , Hannes Whittingham , Puria Radmard , Cameron Tice , Edward James Young

Chain-of-thought (CoT) reasoning provides a significant performance uplift to LLMs by enabling planning, exploration, and deliberation of their actions. CoT is also a powerful tool for monitoring the behaviours of these agents: when…

Artificial Intelligence · Computer Science 2026-05-21 Nathaniel Mitrani Hadida , Sassan Bhanji , Cameron Tice , Puria Radmard
‹ Prev 1 2 3 10 Next ›