arXiv:2606. 25013v1 Announce Type: new Abstract: Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts.
By Narutatsu Ri, Abhishek Panigrahi, Sanjeev Arora
The paper introduces TRUST, a token‑level reward model that predicts the correctness of partial chain‑of‑thought (CoT) traces in vision‑language‑action (VLA) policies, enabling monitoring and selective steering of reasoning. On driving and manipulation VLA benchmarks, TRUST improves reasoning accuracy and reduces collision rates and trajectory errors, though its impact on overall task performance varies across tasks. The study defines two evaluation axes—correctability and actionability—to assess when CoT can serve as a runtime safety interface.
By Sathwik Karnik, Joseph JR. Lee, Aryaman Gupta, Somil Bansal
The paper investigates why chain-of-thought (CoT) reasoning in language models is hard to control, attributing the issue to an entropy collapse in the first few tokens after the opening thinking tag. By applying two inference-time interventions—prefilling a single token and banning frequent opening tokens with in-context examples—the authors significantly improve CoT controllability, especially for addition and style tasks. The study also distinguishes between addition/style and suppression controllability, revealing different underlying mechanisms and correlations with monitorability across models.
By Hugh Van Deventer, Dmitrii Troitskii, Laura Ruis
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
arXiv:2608. 03842v1 Announce Type: cross Abstract: When a language model fails on surface-perturbed input (typos, OCR noise, homophones), "which layer is responsible" has three natural operationalizations: where representations diverge most (sensitivity), where restoring clean activations recovers the prediction (causality), and where a small adapter can repair the damage (compensatory capacity) - and we show these three layer maps dissociate.
By Nathan Labiosa, David Buff, Ena Nayak, Erica Donno
arXiv:2511. 05852v4 Announce Type: replace-cross Abstract: Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs).
By Yinjie Cheng, Paul Youssef, Christin Seifert, J\"org Schl\"otterer, Zhixue Zhao