English
Related papers

Related papers: Monitoring Monitorability

200 papers

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

Test-time compute scaling has demonstrated the ability to improve the performance of reasoning language models by generating longer chain-of-thought (CoT) sequences. However, this increase in performance comes with a significant increase in…

Artificial Intelligence · Computer Science 2025-09-24 Adarsha Balaji , Le Chen , Rajeev Thakur , Franck Cappello , Sandeep Madireddy

Large reasoning models (LRMs) spend substantial test-time compute on long chain-of-thought (CoT) traces, but what *characterizes* an effective CoT remains unclear. While prior work reports gains from lengthening CoTs and increasing review…

Machine Learning · Computer Science 2025-09-24 Yunzhen Feng , Julia Kempe , Cheng Zhang , Parag Jain , Anthony Hartshorn

The viability of chain-of-thought (CoT) monitoring hinges on models being unable to reason effectively in their latent representations. Yet little is known about the limits of such latent reasoning in LLMs. We test these limits by studying…

Machine Learning · Computer Science 2026-04-09 Yi Xu , Philipp Jettkant , Laura Ruis

Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs). CoT explicitly encourages the LLM to generate intermediate rationales for solving a problem, by providing a series…

Computation and Language · Computer Science 2023-06-02 Boshi Wang , Sewon Min , Xiang Deng , Jiaming Shen , You Wu , Luke Zettlemoyer , Huan Sun

Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear. We analyze reasoning dynamics in 18 VLMs covering instruction-tuned and…

Computation and Language · Computer Science 2026-04-28 Danae Sánchez Villegas , Samuel Lewis-Lim , Nikolaos Aletras , Desmond Elliott

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

We examine one particular dimension of AI governance: how to monitor and audit AI-enabled products and services throughout the AI development lifecycle, from pre-deployment testing to post-deployment auditing. Combining principles from…

Artificial Intelligence · Computer Science 2026-05-18 Parand A. Alamdari , Toryn Q. Klassen , Sheila A. McIlraith

Learning complex functions that involve multi-step reasoning poses a significant challenge for standard supervised learning from input-output examples. Chain-of-thought (CoT) supervision, which provides intermediate reasoning steps together…

Machine Learning · Statistics 2025-05-23 Awni Altabaa , Omar Montasser , John Lafferty

Chain-of-Thought (CoT) prompting is a widely used inference-time technique for improving reasoning, yet its gains are uneven across tasks. We analyze when and why CoT helps by modeling the step-wise reasoning trajectory as a Markov chain.…

Machine Learning · Computer Science 2026-03-03 Zihan Wang , Yijun Dong , Qi Lei

We propose a variant of chain of thought (CoT) prompting called Program Trace Prompting that makes explanations more observable while preserving the power, generality and flexibility of CoT. In our approach, few-shot CoT demonstrations are…

Computation and Language · Computer Science 2024-10-03 Cassandra A. Cohen , William W. Cohen

Recent advancements in Chain-of-Thought (CoT) reasoning utilize complex modules but are hampered by high token consumption, limited applicability, and challenges in reproducibility. This paper conducts a critical evaluation of CoT…

Computation and Language · Computer Science 2024-06-12 Mengru Ding , Hanmeng Liu , Zhizhang Fu , Jian Song , Wenbo Xie , Yue Zhang

Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horizon attack patterns. Agents may pursue hidden objectives while maintaining superficially…

Machine Learning · Computer Science 2026-05-26 Nesreen K. Ahmed , Nima Nafisi

Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models (LLMs) on complex tasks, spurring research into its underlying mechanisms. However, two primary challenges remain for real-world applications: (1) the…

Computation and Language · Computer Science 2025-05-20 Qiguang Chen , Libo Qin , Jinhao Liu , Yue Liao , Jiaqi Wang , Jingxuan Zhou , Wanxiang Che

Chain-of-thought (CoT) supervision can substantially improve transformer performance, yet the mechanisms by which models learn to follow and benefit from CoT remain poorly understood. We investigate these learning dynamics through the lens…

Machine Learning · Computer Science 2025-10-31 Zihan Pengmei , Costas Mavromatis , Zhengyuan Shen , Yunyi Zhang , Vassilis N. Ioannidis , Huzefa Rangwala

The ability to perform Chain-of-Thought (CoT) reasoning marks a major milestone for multimodal models (MMs), enabling them to solve complex visual reasoning problems. Yet a critical question remains: is such reasoning genuinely grounded in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Jusheng Zhang , Kaitong Cai , Xiaoyang Guo , Sidi Liu , Qinhan Lv , Ruiqi Chen , Jing Yang , Yijia Fan , Xiaofei Sun , Jian Wang , Ziliang Chen , Liang Lin , Keze Wang

As AI and machine-learned software are used increasingly for making decisions that affect humans, it is imperative that they remain fair and unbiased in their decisions. To complement design-time bias mitigation measures, runtime…

Artificial Intelligence · Computer Science 2023-08-02 Thomas A. Henzinger , Konstantin Kueffner , Kaushik Mallik

Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To address this, we introduce Behavior Cue Reasoning for making LLM reasoning more controllable…

Artificial Intelligence · Computer Science 2026-05-21 Christopher Z. Cui , Taylor W. Killian , Prithviraj Ammanabrolu

Long chain-of-thought (CoT) is an essential ingredient in effective usage of modern large language models, but our understanding of the reasoning strategies underlying these capabilities remains limited. While some prior works have…

Computation and Language · Computer Science 2025-05-16 Seongyun Lee , Seungone Kim , Minju Seo , Yongrae Jo , Dongyoung Go , Hyeonbin Hwang , Jinho Park , Xiang Yue , Sean Welleck , Graham Neubig , Moontae Lee , Minjoon Seo

Chain-of-Thought (CoT) prompting has marked a significant advancement in enhancing the reasoning capabilities of large language models (LLMs). Previous studies have developed various extensions of CoT, which focus primarily on enhancing…

Computation and Language · Computer Science 2025-05-20 Xin Xu , Shizhe Diao , Can Yang , Yang Wang