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

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

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning
Jun 5

State commitment learning: training language models to distinguish computation from memory

arXiv:2606. 05201v1 Announce Type: new Abstract: Reasoning language models do not distinguish tokens used for computation from tokens that constitute persistent state: once generated, all hidden thoughts remain in context and influence future predictions.

By Fei Ding, Yongkang Zhang, Runhao Liu, Yuhao Liao, Zijian Zeng, Huiming Yang
arXiv AI
Aug 24

Knowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation

The paper identifies a specific issue in supervised fine‑tuning (SFT) of large language models called factual access failure, where models can recognize correct facts under constrained tests but fail to generate them in open‑ended settings. It demonstrates that SFT can cause both genuine wrong answers and expression‑level errors such as verbosity or formatting mismatches. To mitigate this, the authors propose Recall‑Anchored Distillation (RAD), a self‑distillation method that aligns the fine‑tuned model with the base model’s soft output distribution on unlabeled out‑of‑distribution text, thereby recovering lost factual recall without needing labeled data.

By Haodong Chen, Yadong Wang, Shengtao Wen, Dong Liang, Xiang Chen
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
arXiv AI
Sep 17

First Token Matters: Understanding Safety Collapse in Large Reasoning Models

The paper investigates why large reasoning models (LRMs) lose safety alignment when faced with harmful queries. By analyzing token-level refusal dynamics, the authors identify a vulnerability called Onset Refusal Collapse (ORC), where the refusal signal drops sharply at the first generated token, leading to unsafe responses. They introduce SafeToken, a lightweight inference-time intervention that injects a learned safety anchor at reasoning onset, which mitigates ORC, improves safety on harmful-query benchmarks, and largely preserves reasoning utility.

By Yizheng Yang, Haining Yu, Yuechen Wang, Yikai Hou, Xing Fu, Jinbo Yang, Tianqing Zhu