English
Related papers

Related papers: Auditing Reasoning-Trace Memorization Claims after…

200 papers

Intelligent tutoring systems increasingly provide automated feedback on student work, but robust feedback requires assessing reasoning, not only final answers. We study a failure mode we call the correct answer trap (CAT): models…

Computers and Society · Computer Science 2026-05-26 Moiz Imran , Sahan Bulathwela

Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We introduce Inference-Time Rethinking, a generative framework…

Computation and Language · Computer Science 2026-02-09 Deqian Kong , Minglu Zhao , Aoyang Qin , Bo Pang , Chenxin Tao , David Hartmann , Edouardo Honig , Dehong Xu , Amit Kumar , Matt Sarte , Chuan Li , Jianwen Xie , Ying Nian Wu

Reasoning models have achieved remarkable performance on tasks like math and logical reasoning thanks to their ability to search during reasoning. However, they still suffer from overthinking, often performing unnecessary reasoning steps…

Artificial Intelligence · Computer Science 2025-04-09 Anqi Zhang , Yulin Chen , Jane Pan , Chen Zhao , Aurojit Panda , Jinyang Li , He He

Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance frameworks increasingly require deleting sensitive data from…

Machine Learning · Computer Science 2026-04-21 Anna Mazhar , Sainyam Galhotra

Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks, yet their ability to perform multi-step logical reasoning remains an open challenge. Although Chain-of-Thought prompting has…

Extended-thinking models expose a second text-generation channel ("thinking tokens") alongside the user-visible answer. This study examines 12 open-weight reasoning models on MMLU and GPQA questions paired with misleading hints. Among the…

Computation and Language · Computer Science 2026-03-30 Richard J. Young

Identifying the training datasets that influence a language model's outputs is essential for minimizing the generation of harmful content and enhancing its performance. Ideally, we can measure the influence of each dataset by removing it…

Computation and Language · Computer Science 2024-06-14 Masaru Isonuma , Ivan Titov

The dictionary learning problem, representing data as a combination of a few atoms, has long stood as a popular method for learning representations in statistics and signal processing. The most popular dictionary learning algorithm…

Machine Learning · Computer Science 2022-08-04 Bahareh Tolooshams , Demba Ba

Large language models readily memorize arbitrary training instances, such as label noise, yet they perform strikingly well on reasoning tasks. In this work, we investigate how language models memorize label noise, and why such memorization…

Computation and Language · Computer Science 2025-10-03 Yupei Du , Philipp Mondorf , Silvia Casola , Yuekun Yao , Robert Litschko , Barbara Plank

Machine unlearning poses challenges in removing mislabeled, contaminated, or problematic data from a pretrained model. Current unlearning approaches and evaluation metrics are solely focused on model predictions, which limits insight into…

Machine Learning · Computer Science 2026-04-13 Khoa Tran , Simon S. Woo

Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in their chain-of-thought reasoning. This makes the detection…

Computation and Language · Computer Science 2025-07-15 Miles Turpin , Andy Arditi , Marvin Li , Joe Benton , Julian Michael

Recently, deep reasoning LLMs (e.g., OpenAI o1 and DeepSeek-R1) have shown promising performance in various downstream tasks. Free translation is an important and interesting task in the multilingual world, which requires going beyond…

Computation and Language · Computer Science 2025-09-01 Jiaan Wang , Fandong Meng , Jie Zhou

Machine unlearning, which enables a model to forget specific data, is crucial for ensuring data privacy and model reliability. However, its effectiveness can be severely undermined in real-world scenarios where models learn unintended…

Machine Learning · Computer Science 2026-02-26 JuneHyoung Kwon , MiHyeon Kim , Eunju Lee , Yoonji Lee , Seunghoon Lee , YoungBin Kim

Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining. This capability is crucial for ensuring privacy, safety, and regulatory compliance. Therefore, verifying whether a…

Computation and Language · Computer Science 2025-11-07 Liran Cohen , Yaniv Nemcovesky , Avi Mendelson

Recent think-answer approaches in VLMs, such as Qwen3-VL-Thinking, boost reasoning performance by leveraging intermediate thinking steps before the final answer, but their computational cost becomes substantial, especially for larger VLMs.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-27 Seonghoon Yu , Dongjun Nam , Byung-Kwan Lee , Jeany Son

Machine unlearning seeks to remove the influence of specified data from a trained model. While the unlearning accuracy provides a widely used metric for assessing unlearning performance, it falls short in assessing the reliability of…

Machine Learning · Computer Science 2026-05-13 Yingdan Shi , Sijia Liu , Kaize Ding , Ren Wang

Large Language Model interfaces are increasingly verbose, exposing intermediate reasoning traces alongside final answers. Traces are framed as transparency mechanisms, yet it is unclear how people use them to solve problems. We report a…

Human-Computer Interaction · Computer Science 2026-05-26 Daniela Fernandes , Daniel Buschek , Lev Tankelevitch , Thomas Kosch , Robin Welsch

Recent reasoning models show the ability to reflect, backtrack, and self-validate their reasoning, which is crucial in spotting mistakes and arriving at accurate solutions. A natural question that arises is how effectively models can…

Computation and Language · Computer Science 2025-09-25 Sohee Yang , Sang-Woo Lee , Nora Kassner , Daniela Gottesman , Sebastian Riedel , Mor Geva

Incorporating explicit reasoning rules within the latent space of language models (LMs) offers a promising pathway to enhance generalisation, interpretability, and controllability. While current Transformer-based language models have shown…

Computation and Language · Computer Science 2025-10-13 Yingji Zhang , Marco Valentino , Danilo S. Carvalho , André Freitas

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning…