English
Related papers

Related papers: Auditing Reasoning-Trace Memorization Claims after…

200 papers

Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find a previously undocumented failure mode: the…

Artificial Intelligence · Computer Science 2026-05-29 Yubo Li , Ramayya Krishnan , Rema Padman

Recent advances in large reasoning models (LRMs) have enabled strong chain-of-thought (CoT) generation through test-time computation. While these multi-step reasoning capabilities represent a major milestone in language model performance,…

Artificial Intelligence · Computer Science 2025-10-14 Changsheng Wang , Chongyu Fan , Yihua Zhang , Jinghan Jia , Dennis Wei , Parikshit Ram , Nathalie Baracaldo , Sijia Liu

Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on ordinary instruction-response data that contains no such traces. We show that this…

Machine Learning · Computer Science 2026-05-21 Lukas Twist , Helen Yannakoudakis , Jie M. Zhang

Machine unlearning has emerged as a prevalent technical solution for selectively removing unwanted knowledge absorbed during pre-training, without requiring full retraining. While recent unlearning techniques can effectively remove…

Machine Learning · Computer Science 2025-11-04 Myeongseob Ko , Hoang Anh Just , Charles Fleming , Ming Jin , Ruoxi Jia

Chain-of-thought (CoT) prompting has become central to mathematical reasoning in large language models, yet models remain brittle to early errors: a single arithmetic slip or unjustified inference typically propagates uncorrected to an…

Machine Learning · Computer Science 2025-12-22 Saraswathy Amjith , Mihika Dusad , Neha Muramalla , Shweta Shah

A distinction is often drawn between a model's ability to predict a label for an evaluation sample that is directly memorised from highly similar training samples versus an ability to predict the label via some method of generalisation. In…

Computation and Language · Computer Science 2023-11-22 Tim Hartill , Joshua Bensemann , Michael Witbrock , Patricia J. Riddle

Chain-of-thought (CoT) distillation trains a smaller model to imitate a teacher's reasoning trace, but it is typically evaluated by final-answer metrics including accuracy. We ask whether gains in answer quality are accompanied by…

Artificial Intelligence · Computer Science 2026-05-28 Zhaoyang Jiang , Xuanqi Peng , Fei Teng , Zhizhong Fu , Yunsoo Kim , Jiacong Mi , Zicheng Li , Honghan Wu

Knowledge distillation is a widely adopted technique for transferring capabilities from LLMs to smaller, more efficient student models. However, unauthorized use of knowledge distillation takes unfair advantage of the considerable effort…

Artificial Intelligence · Computer Science 2026-04-20 Xinhang Ma , William Yeoh , Ning Zhang , Yevgeniy Vorobeychik

Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall…

Machine Learning · Computer Science 2026-03-16 Harshwardhan Fartale , Ashish Kattamuri , Rahul Raja , Arpita Vats , Ishita Prasad , Akshata Kishore Moharir

The scalability of large language models for long-context reasoning is severely constrained by the linear growth of their Transformer key-value cache, which incurs significant memory and computational costs. We posit that as a model…

Computation and Language · Computer Science 2025-12-30 Giovanni Monea , Yair Feldman , Shankar Padmanabhan , Kianté Brantley , Yoav Artzi

For Large Language Models (LLMs) to be reliably deployed, models must effectively know when not to answer: abstain. Reasoning models, in particular, have gained attention for impressive performance on complex tasks. However, reasoning…

Artificial Intelligence · Computer Science 2026-04-03 Abinitha Gourabathina , Inkit Padhi , Manish Nagireddy , Subhajit Chaudhury , Prasanna Sattigeri

Scaled post-training now drives many of the largest capability gains in language models (LMs), yet its effect on pretrained knowledge remains poorly understood. Not all forgetting is equal: Forgetting one fact (e.g., a U.S. president or an…

Machine Learning · Computer Science 2025-10-21 Jackson Harmon , Andreas Hochlehnert , Matthias Bethge , Ameya Prabhu

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…

Unlearning in Large Language Models (LLMs) aims to enhance safety, mitigate biases, and comply with legal mandates, such as the right to be forgotten. However, existing unlearning methods are brittle: minor query modifications, such as…

Artificial Intelligence · Computer Science 2026-03-13 Raj Sanjay Shah , Jing Huang , Keerthiram Murugesan , Nathalie Baracaldo , Diyi Yang

Test-time compute is central to large reasoning models, yet analysing their reasoning behaviour through generated text is increasingly impractical and unreliable. Response length is often used as a brute proxy for reasoning effort, but this…

Computation and Language · Computer Science 2026-02-09 Quoc Tuan Pham , Mehdi Jafari , Flora Salim

Large Reasoning Models (LRMs) embed private or copyrighted information not only in their final answers but also throughout multi-step chain-of-thought (CoT) traces, making reliable unlearning far more demanding than in standard LLMs. We…

Computation and Language · Computer Science 2025-05-28 Sangyeon Yoon , Wonje Jeung , Albert No

Fine-tuning large language models (LLMs) is intended to improve their reasoning capabilities, yet we uncover a counterintuitive effect: models often forget how to solve problems they previously answered correctly during training. We term…

Artificial Intelligence · Computer Science 2025-05-27 Yuetai Li , Zhangchen Xu , Fengqing Jiang , Bhaskar Ramasubramanian , Luyao Niu , Bill Yuchen Lin , Xiang Yue , Radha Poovendran

Large Reasoning Models (LRMs) allocate substantial inference-time compute to Chain-of-Thought (CoT) reasoning, improving performance on mathematics, scientific QA, and tool usage. However, this introduces overthinking: LRMs often reach a…

Computation and Language · Computer Science 2026-04-21 Sangjun Song , Minjae Oh , Seungkyu Lee , Sungmin Jo , Yohan Jo

Scaling test-time compute via Long Chain-of-Thought (Long-CoT) significantly enhances reasoning capabilities, yet extended generation does not guarantee correctness: after an early wrong commitment, models may keep elaborating a…

Artificial Intelligence · Computer Science 2026-01-21 Kang Chen , Fan Yu , Junjie Nian , Shihan Zhao , Zhuoka Feng , Zijun Yao , Heng Wang , Minshen Yu , Yixin Cao

While reasoning models are increasingly ubiquitous, the effects of reasoning training on a model's internal mechanisms remain poorly understood. In this work, we introduce transcoder adapters, a technique for learning an interpretable…

Machine Learning · Computer Science 2026-02-25 Nathan Hu , Jake Ward , Thomas Icard , Christopher Potts
‹ Prev 1 2 3 10 Next ›