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.
arXiv:2607. 02914v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet ensuring their simultaneous safety, helpfulness, and trustworthiness remains a persistent challenge.
arXiv:2606. 00869v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become central to LLM reasoning, but its outcome-level rewards can make models more willing to give confident answers when evidence or reasoning is unreliable.
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.
arXiv:2511. 21214v4 Announce Type: replace-cross Abstract: Explicit safety policies can improve reasoning-model safety, but their effective coverage may lag behind evolving jailbreak strategies.
arXiv:2604. 23270v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs).
arXiv:2606. 31748v1 Announce Type: new Abstract: Safety training on language models often induces over-refusal: improved safety on harmful prompts at the cost of increased refusal on harmless ones.
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:2608. 03745v1 Announce Type: new Abstract: Chain-of-Thought (CoT) reasoning offers a promising window into model monitoring.
The paper investigates how different post‑training methods—supervised fine‑tuning, reasoning‑augmented fine‑tuning, and preference optimization (ORPO)—affect the internal computation of refusal behavior in language models. Experiments on Llama‑3.1‑8B, Gemma‑2‑9B, and Qwen3‑8B show that reasoning‑augmented training consistently creates a distinct refusal computation across models, while the architecture influences the internal structure and steerability of refusal. None of the studied methods simultaneously achieve a distributed refusal mechanism, preserve general capability, and allow easy corrective edits, indicating that current post‑training approaches are not a fully reliable defense for safety-critical applications.
arXiv:2602. 09305v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable.
arXiv:2602. 12124v2 Announce Type: replace Abstract: While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerable environments.
Negative Self-Distillation (NSD) is a new framework for improving large language models by encouraging them to diverge from their own flawed reasoning rather than imitate privileged solutions. Unlike On-Policy Self-Distillation, which can suppress uncertainty and exploratory behavior, NSD generates a question‑specific negative condition (e.g., a careless reasoner) and uses a dynamic gating mechanism to target only reasoning‑critical tokens for penalization. This approach preserves foundational language capabilities while consistently outperforming OPSD and other label‑free self‑bootstrapping reinforcement learning baselines.