Reasoning Structure Matters for Safety Alignment of Reasoning Models

• URL: http://arxiv.org/abs/2604.18946v1
• Date: Tue, 21 Apr 2026 00:50:13 GMT
• Title: Reasoning Structure Matters for Safety Alignment of Reasoning Models
• Abstract summary: Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries.<n>This paper investigates the underlying cause of these safety risks and shows that the issue lies in the reasoning structure itself.<n>We propose AltTrain, a simple yet effective post training method that explicitly alters the reasoning structure of LRMs.
• Score: 15.132886571424622
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. This paper investigates the underlying cause of these safety risks and shows that the issue lies in the reasoning structure itself. Based on this insight, we claim that effective safety alignment can be achieved by altering the reasoning structure. We propose AltTrain, a simple yet effective post training method that explicitly alters the reasoning structure of LRMs. AltTrain is both practical and generalizable, requiring no complex reinforcement learning (RL) training or reward design, only supervised finetuning (SFT) with a lightweight 1K training examples. Experiments across LRM backbones and model sizes demonstrate strong safety alignment, along with robust generalization across reasoning, QA, summarization, and multilingual setting.

Related papers

• Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms [43.21675006313594]
  This paper investigates the underlying cause of safety degradation in large language models (LLMs)<n>We propose a lightweight and cost-effective solution called SafeReAct that restores the suppressed safety behaviors by aligning with LoRA adapters.<n> Experiments on four state-of-the-art LRMs show that our method significantly improves safety on harmful prompts without compromising reasoning performance.
  arXiv  Detail & Related papers  (2026-03-10T06:56:23Z)
• Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability [18.931331452604066]
  Large reasoning models (LRMs) extend large language models by generating explicit chain-of-thought (CoT) reasoning.<n>Existing safety alignment approaches rely on supervised fine-tuning (SFT) over safety-oriented long CoT datasets.<n>We investigate reinforcement learning (RL) as a complementary optimization framework for LRM safety training.
  arXiv  Detail & Related papers  (2025-12-01T16:35:34Z)
• When Models Outthink Their Safety: Mitigating Self-Jailbreak in Large Reasoning Models with Chain-of-Guardrails [74.63933201261595]
  Large Reasoning Models (LRMs) demonstrate remarkable capabilities on complex reasoning tasks.<n>LRMs remain vulnerable to severe safety risks, including harmful content generation and jailbreak attacks.<n>We propose the Chain-of-Guardrail (CoG), a training framework that recomposes or backtracks unsafe reasoning steps.
  arXiv  Detail & Related papers  (2025-10-24T09:32:25Z)
• Large Reasoning Models Learn Better Alignment from Flawed Thinking [56.08883934423522]
  Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer.<n>We propose RECAP, a principled reinforcement learning (RL) method for post-training that explicitly teaches models to override flawed reasoning trajectories.
  arXiv  Detail & Related papers  (2025-10-01T14:15:43Z)
• AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models [62.70575022567081]
  We propose AdvChain, an alignment paradigm that teaches models dynamic self-correction through adversarial CoT tuning.<n>Our work establishes a new direction for building more robust and reliable reasoning models.
  arXiv  Detail & Related papers  (2025-09-29T04:27:23Z)
• R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge [16.653490433862224]
  We investigate the underlying cause of LRM safety risks and find that models already possess sufficient safety knowledge but fail to activate it during reasoning.<n>We propose R1-Act, a simple and efficient post-training method that explicitly triggers safety knowledge through a structured reasoning process.<n>R1-Act achieves strong safety improvements while preserving reasoning performance, outperforming prior alignment methods.
  arXiv  Detail & Related papers  (2025-08-01T05:14:13Z)
• Distilling the Implicit Multi-Branch Structure in LLMs' Reasoning via Reinforcement Learning [63.888013006686364]
  Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of Large Language Models (LLMs)<n>We propose RLKD, a reinforcement learning-based distillation framework guided by a novel Generative Structure Reward Model (GSRM)<n>Our GSRM converts reasoning paths into multiple meta-reasoning-solving steps and computes rewards to measure structural alignment between student and teacher reasoning.
  arXiv  Detail & Related papers  (2025-05-22T02:36:36Z)
• How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study [90.34190170330481]
  Large Reasoning Models (LRMs) have achieved remarkable success on reasoning-intensive tasks such as mathematics and programming.<n>However, their enhanced reasoning capabilities do not necessarily translate to improved safety performance.<n>We present a comprehensive empirical study on how to enhance the safety of LRMs through Supervised Fine-Tuning.
  arXiv  Detail & Related papers  (2025-05-21T11:45:29Z)
• Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning [23.99454995087634]
  We explore the potential of rule-based reinforcement learning in large reasoning models.<n>We use synthetic logic puzzles as training data due to their controllable complexity and straightforward answer verification.<n>Our 7B model develops advanced reasoning skills-such as reflection, verification, and summarization-that are absent from the logic corpus.
  arXiv  Detail & Related papers  (2025-02-20T17:49:26Z)
• Safety Reasoning with Guidelines [63.15719512614899]
  Refusal Training (RT) struggles to generalize against various Out-of-Distribution (OOD) jailbreaking attacks.<n>We propose training model to perform safety reasoning for each query.
  arXiv  Detail & Related papers  (2025-02-06T13:01:44Z)
• Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning [52.83539473110143]
  We introduce a novel structure-oriented analysis method to help Large Language Models (LLMs) better understand a question. To further improve the reliability in complex question-answering tasks, we propose a multi-agent reasoning system, Structure-oriented Autonomous Reasoning Agents (SARA) Extensive experiments verify the effectiveness of the proposed reasoning system. Surprisingly, in some cases, the system even surpasses few-shot methods.
  arXiv  Detail & Related papers  (2024-10-18T05:30:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.