English
Related papers

Related papers: Monitoring Reasoning Models for Misbehavior and th…

200 papers

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this…

Cryptography and Security · Computer Science 2026-04-28 Yuansen Liu , Yixuan Tang , Anthony Kum Hoe Tun

Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence remains challenging because true task rewards are often…

Machine Learning · Computer Science 2026-04-21 Muhammad Khalifa , Zohaib Khan , Omer Tafveez , Hao Peng , Lu Wang

Chain-of-thought (CoT) prompting combined with few-shot in-context learning (ICL) has unlocked significant reasoning capabilities in large language models (LLMs). However, ICL with CoT examples is ineffective on novel tasks when the…

Computation and Language · Computer Science 2025-12-08 Vignesh Kothapalli , Ata Fatahibaarzi , Hamed Firooz , Maziar Sanjabi

Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal…

Computation and Language · Computer Science 2023-09-06 Peiyi Wang , Lei Li , Liang Chen , Feifan Song , Binghuai Lin , Yunbo Cao , Tianyu Liu , Zhifang Sui

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

Alignment techniques often inadvertently induce sycophancy in LLMs. While prior studies studied this behaviour in direct-answer settings, the role of Chain-of-Thought (CoT) reasoning remains under-explored: does it serve as a logical…

Computation and Language · Computer Science 2026-03-18 Zhaoxin Feng , Zheng Chen , Jianfei Ma , Yip Tin Po , Emmanuele Chersoni , Bo Li

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

Recently, o1-like models have drawn significant attention, where these models produce the long Chain-of-Thought (CoT) reasoning steps to improve the reasoning abilities of existing Large Language Models (LLMs). In this paper, to understand…

Computation and Language · Computer Science 2025-04-01 Yancheng He , Shilong Li , Jiaheng Liu , Weixun Wang , Xingyuan Bu , Ge Zhang , Zhongyuan Peng , Zhaoxiang Zhang , Zhicheng Zheng , Wenbo Su , Bo Zheng

Language models (LMs) with less than 100B parameters are known to perform poorly on chain-of-thought (CoT) reasoning in contrast to large LMs when solving unseen tasks. In this work, we aim to equip smaller LMs with the step-by-step…

Computation and Language · Computer Science 2023-10-17 Seungone Kim , Se June Joo , Doyoung Kim , Joel Jang , Seonghyeon Ye , Jamin Shin , Minjoon Seo

Large language models have demonstrated remarkable progress in mathematical reasoning, leveraging chain-of-thought and test-time compute scaling. However, many open questions remain regarding the interplay between reasoning token usage and…

Machine Learning · Computer Science 2025-02-24 Marthe Ballon , Andres Algaba , Vincent Ginis

Scaling inference compute enhances reasoning in large language models (LLMs), with long chains-of-thought (CoTs) enabling strategies like backtracking and error correction. Reinforcement learning (RL) has emerged as a crucial method for…

Computation and Language · Computer Science 2025-02-06 Edward Yeo , Yuxuan Tong , Morry Niu , Graham Neubig , Xiang Yue

Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. To address this issue, efficient reasoning aims to incentivize short yet accurate thinking…

Computation and Language · Computer Science 2026-03-23 Taiqiang Wu , Zenan Xu , Bo Zhou , Ngai Wong

Recent advances in fine-tuning large language models (LLMs) with reinforcement learning (RL) have shown promising improvements in complex reasoning tasks, particularly when paired with chain-of-thought (CoT) prompting. However, these…

Machine Learning · Computer Science 2025-04-04 Hung Le , Dai Do , Dung Nguyen , Svetha Venkatesh

The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be…

Artificial Intelligence · Computer Science 2025-06-06 Kai Wang , Yihao Zhang , Meng Sun

In recent years, the detection of AI-generated text has become a critical area of research due to concerns about academic integrity, misinformation, and ethical AI deployment. This paper presents COT Fine-tuned, a novel framework for…

Computation and Language · Computer Science 2025-04-24 Shifali Agrahari , Sanasam Ranbir Singh

Chain-of-Thought (CoT) prompting has improved the reasoning performance of large language models (LLMs), but it remains unclear why it works and whether it is the unique mechanism for triggering reasoning in large language models. In this…

Computation and Language · Computer Science 2026-01-14 Zhenghao He , Guangzhi Xiong , Bohan Liu , Sanchit Sinha , Aidong Zhang

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

AI Agents rely on Large Language Models (LLMs) and Multimodal-LLMs (MLLMs) to perform interpretation and inference in text and image tasks without post-training, where LLMs and MLLMs play the most critical role and determine the initial…

Artificial Intelligence · Computer Science 2025-07-14 Haoran Sun , Shaoning Zeng

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically…

Cryptography and Security · Computer Science 2026-03-17 Yu Pan , Wenlong Yu , Tiejun Wu , Xiaohu Ye , Qiannan Si , Guangquan Xu , Bin Wu

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and…

Cryptography and Security · Computer Science 2026-04-30 Matteo Leonesi , Francesco Belardinelli , Flavio Corradini , Marco Piangerelli
‹ Prev 1 4 5 6 7 8 10 Next ›