arXiv AI

REDaCT: Collapse-Free Unlearning in Large Reasoning Models

The paper introduces REDaCT, an inference-time unlearning framework for large reasoning models that removes forget-set information from both the reasoning trace and the final answer without causing reasoning collapse. REDaCT uses a binary leak detector to spot sentences that leak forget-set data and an embedding optimization module that injects a corrective embedding at the first detected leak, steering subsequent reasoning toward non-leaking sentences. Experiments demonstrate that REDaCT preserves coherent chain-of-thought reasoning, outperforms existing unlearning methods, and achieves perfect answer forgetting with near-perfect chain-of-thought forgetting.

arXiv AI

Sep 21

GUARD: Natural Forgetting in Large Reasoning Models via Guided Answer-Reasoning Distillation

The paper introduces GUARD, a method for natural forgetting in large reasoning models that transforms unsafe disclosures into safe-exit trajectories using guided answer‑reasoning distillation. It aligns a frozen model with guidance tokens and distills this behavior into the parameters, aiming for a coherent, non‑disclosing chain of thought followed by a refusal‑style answer. The authors also propose the Natural Forgetting Reasoning Score (NFRS) to evaluate structural stability, fluency, and unsupported substitutes, and demonstrate GUARD’s effectiveness on R‑TOFU and a STAR‑1‑derived harmful‑intent setting.

By Zeyu Yan, Guanghao Zhou, Minghui Qiu, Ming Gao, Cen Chen

efficiency safety

arXiv Machine Learning

Jul 13

Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem

arXiv:2607. 09236v1 Announce Type: new Abstract: Machine unlearning in LLMs is the targeted removal of specific knowledge while preserving all other capabilities, critical for privacy and safety.

By Amit Peleg, Naman Deep Singh, Naama Pearl, Bibhabasu Mohapatra, Matthias Hein

llms benchmarks safety

arXiv Computation and Language

Oct 1

Offline Guidance, Online Reasoning: Reusing LLM Feedback for Small Language Models

arXiv:2609.39346v1 Announce Type: new Abstract: Large language models (LLMs) offer strong reasoning capabilities but are often costly to access through commercial APIs, while small language models (S...

By Bohan Zhang (Southeast University), Linan Yue (Southeast University), Weibo Gao (Hong Kong Polytechnic University), Pengyu Chen (Southeast University), Hong Guo (Southeast University), Yanqi Hao (ZTE Corporation)

llms efficiency benchmarks

arXiv Computation and Language

Oct 15

To Reason but Not to Stop: Understanding and Recovering Pruned Large Reasoning Models

arXiv:2610.19934v1 Announce Type: new Abstract: Weight pruning can degrade the accuracy of large reasoning models (LRMs), yet it remains unclear whether it damages reasoning itself. We find that much...

By Minh-Anh Nguyen, Nguyen T. Ha Lan, Xiyan Fu, Dung D. Le, Wei Lu

efficiency benchmarks

arXiv AI

Aug 25

Is Next-Chunk Reasoning RL Really Better than SFT? Revisiting Training Strategies under no-CoT Data

arXiv:2608.23256v1 Announce Type: new Abstract: Recent work proposes next-chunk reasoning RL for leveraging no-CoT data---corpora such as worked solutions and textbook derivations that contain reason...

By Yinhao Tang, Youqing Fang, Yanan Sun, Jiangning Liu, Ziyi Wang, Xun Zhao, Weiming Zhang, Bin Liu, Kuikun Liu, Wenwei Zhang, Kai Chen

reinforcement-learning fine-tuning

arXiv AI

Jun 19

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

arXiv:2510. 21978v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models.

By Hoang Phan, Xianjun Yang, Yuanshun Yao, Jingyu Zhang, Shengjie Bi, Xiaocheng Tang, Madian Khabsa, Lijuan Liu, Deren Lei

llms reinforcement-learning multimodal benchmarks

Hugging Face Trending Papers

Jul 29

ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models

Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowledge under repeated updates remains insufficiently understood. Existing evaluation paradigms primarily focus on single-step reasoning or static knowledge editing, which fail to capture the temporal dynamics of knowledge retention and degradation during continual model modification.

llms benchmarks

arXiv AI

Jul 31

ForgetBench: Benchmarking Forgetting Dynamics of Long-Term Parametric Memory in Language Models

arXiv:2607. 26455v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquired knowledge under repeated updates remains insufficiently understood.

By Ruxi Gu, Zhenliang Zhang, Wei Wang

llms benchmarks

arXiv AI

Sep 30

CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory

CoEM introduces a Commit-on-Evidence Memory system that learns when to compress source evidence into compact memory facts while preserving potentially useful excerpts verbatim in a pending set. The system uses a learned policy to decide whether to promote, retain, or discard each pending excerpt as new context arrives, and a frozen verifier ensures only supported facts are committed. Reinforcement learning trains this policy with step-level evidence rewards and final answer rewards, leading to consistent improvements in long-context reasoning, achieving 10.4–11.4 F1 points over the strongest baseline on 6,400-document inputs.

By Jingguang Li, Yebo Wu, Zuyi Guo, Kailang Ma, Xianjie Dai, Han Zheng, Benwang Chen, Li Li, Can Rong, Heye Huang

llms reinforcement-learning

arXiv AI

Jul 21

When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs

arXiv:2510. 22228v2 Announce Type: replace-cross Abstract: Layer pruning has emerged as a widely adopted technique for improving the efficiency of large language models (LLMs).

By Keyu Wang, Tian Lyu, Guinan Su, Lu Yin, Marco Canini, Jonas Geiping, Shiwei Liu

llms fine-tuning efficiency benchmarks

arXiv AI

Sep 1

Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models

arXiv:2509.24711v4 Announce Type: replace Abstract: Current answering paradigms for Large Reasoning Models (LRMs) often fail to account for the fact that some questions may lie beyond the model's ope...

By Qingjie Zhang, Yujia Fu, Yang Wang, Liu Yan, Tao Wei, Ke Xu, Minlie Huang, Han Qiu

arXiv AI

Jun 30

Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning

arXiv:2508. 02178v3 Announce Type: replace Abstract: Large reasoning models (LRMs) often exhibit overthinking, producing verbose Chain-of-Thought (CoT) traces that increase inference cost and obscure the underlying reasoning process.

By Taihang Zhen, Jialiang Hong, Kai Chen, Guang Yang, Junlan Feng, Wenpeng Zhu, Jing Huo, Yang Gao, Depeng Wang, Haitao Wan, Xi Yang, Fanyu Meng, Yuyao Zhang, Ji Qi, Xiangyu Zhou

reinforcement-learning

Related stories