Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with chain-of-thought traces can induce harmful beha...
arXiv:2605.01913v2 Announce Type: replace-cross Abstract: Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vul...
The paper introduces SaLT-DPO, a Segment‑aware Listwise Target DPO method designed to improve safety in Large Reasoning Models (LRMs). It decomposes responses into reasoning and answer segments, scores each segment’s safety, and aligns length‑normalized rewards with soft target distributions over multiple candidates. The approach also incorporates joint safety coherence regularization and utility anchoring to reduce unsafe content while maintaining compliance and reasoning performance.
arXiv:2607. 16242v1 Announce Type: cross Abstract: Fine-Tuning-as-a-Service (FTaaS) platforms let users train large language models (LLMs) on customized tasks, but this pipeline could erode models' safety alignment.
arXiv:2608. 03745v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning offers a promising window into model monitoring.
arXiv:2609.08186v1 Announce Type: new Abstract: The emergence of Chain-of-Thought (CoT) has established a robust foundation for Large Reasoning Models (LRMs). While deep reasoning is widely believed...
arXiv:2605.28006v2 Announce Type: replace-cross Abstract: Understanding how LLMs reason is hindered by a practical asymmetry: while their generated outputs are observable, the underlying reasoning pa...
arXiv:2606. 07410v1 Announce Type: cross Abstract: The emergence of "Aha moments" in large language models, particularly DeepSeek-R1-0120, has raised the question of whether these systems genuinely reason or merely imitate the appearance of reasoning.
arXiv:2604. 06628v2 Announce Type: replace Abstract: A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes.
arXiv:2602. 13562v2 Announce Type: replace-cross Abstract: While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures.
The paper introduces "cunning questions"—non‑safety prompts that contain misleading premises or subtle inconsistencies—to train large language models (LLMs) to scrutinize underlying intent and assumptions. Experiments show that incorporating these questions improves robustness against out‑of‑distribution jailbreak attacks and enhances subsequent safety fine‑tuning, achieving a new state‑of‑the‑art reduction in mean ASR from 17.40% to 15.05% across nine backbone–benchmark combinations. The authors argue that this training fosters vigilance, enabling models to prioritize safety judgments before engaging in harmful planning.
Large reasoning models generate chain-of-thought (CoT) before answering but struggle with safety alignment and can be misled by flawed premises. The paper introduces RECAP, a reinforcement learning approach that trains models to override flawed reasoning paths and produce safe, helpful responses without extra training cost. RECAP improves safety, jailbreak robustness, and reduces overrefusal while preserving core reasoning abilities and inference token budget.