RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards

• URL: http://arxiv.org/abs/2506.07736v3
• Date: Fri, 24 Oct 2025 06:18:17 GMT
• Title: RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
• Authors: Jingnan Zheng, Xiangtian Ji, Yijun Lu, Chenhang Cui, Weixiang Zhao, Gelei Deng, Zhenkai Liang, An Zhang, Tat-Seng Chua,
• Abstract summary: Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts.<n>To safeguard against the risk of policy-violating content, system-level moderation via external guard models has emerged as a prevalent mitigation strategy.<n>We propose RSafe, an adaptive reasoning-based safeguard that conducts guided safety reasoning to provide robust protection within the scope of specified safety policies.
• Score: 55.76285458905577
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation via external guard models-designed to monitor LLM inputs and outputs and block potentially harmful content-has emerged as a prevalent mitigation strategy. Existing approaches of training guard models rely heavily on extensive human curated datasets and struggle with out-of-distribution threats, such as emerging harmful categories or jailbreak attacks. To address these limitations, we propose RSafe, an adaptive reasoning-based safeguard that conducts guided safety reasoning to provide robust protection within the scope of specified safety policies. RSafe operates in two stages: 1) guided reasoning, where it analyzes safety risks of input content through policy-guided step-by-step reasoning, and 2) reinforced alignment, where rule-based RL optimizes its reasoning paths to align with accurate safety prediction. This two-stage training paradigm enables RSafe to internalize safety principles to generalize safety protection capability over unseen or adversarial safety violation scenarios. During inference, RSafe accepts user-specified safety policies to provide enhanced safeguards tailored to specific safety requirements.

Related papers

• Self-Guard: Defending Large Reasoning Models via enhanced self-reflection [54.775612141528164]
  Self-Guard is a lightweight safety defense framework for Large Reasoning Models.<n>It bridges the awareness-compliance gap, achieving robust safety performance without compromising model utility.<n>Self-Guard exhibits strong generalization across diverse unseen risks and varying model scales.
  arXiv  Detail & Related papers  (2026-01-31T13:06:11Z)
• Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment [49.2305683068875]
  We propose Risk-aware Stepwise Alignment (RSA), a novel alignment method that incorporates risk awareness into the policy optimization process.<n> RSA mitigates risks induced by excessive model shift away from a reference policy, and it explicitly suppresses low-probability yet high-impact harmful behaviors.<n> Experimental results demonstrate that our method achieves high levels of helpfulness while ensuring strong safety.
  arXiv  Detail & Related papers  (2025-12-30T14:38:02Z)
• SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization [79.14563283347773]
  Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities.<n>Cross-modal couplings can produce unsafe semantics even when individual inputs are benign.<n>We propose SafeGRPO, a self-rewarded multimodal safety alignment framework.
  arXiv  Detail & Related papers  (2025-11-17T05:09:49Z)
• DeepKnown-Guard: A Proprietary Model-Based Safety Response Framework for AI Agents [12.054307827384415]
  Large Language Models (LLMs) have become increasingly prominent, severely constraining their trustworthy deployment in critical domains.<n>This paper proposes a novel safety response framework designed to safeguard LLMs at both the input and output levels.
  arXiv  Detail & Related papers  (2025-11-05T03:04:35Z)
• UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models [67.91151588917396]
  Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks.<n>We propose UpSafe$circ$C, a unified framework for enhancing LLM safety through safety-aware upcycling.<n>Our results highlight a new direction for LLM safety: moving from static alignment toward dynamic, modular, and inference-aware control.
  arXiv  Detail & Related papers  (2025-10-02T16:43:33Z)
• AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning [21.399086197886202]
  Large language models (LLMs) possess latent safety understanding from their vast pretraining data.<n>We propose textbfAlphaAlign, a pure reinforcement learning framework with verifiable safety reward.<n>This allows the model to develop proactive safety reasoning capabilities without depending on supervised safety-specific reasoning data.
  arXiv  Detail & Related papers  (2025-07-20T14:47:03Z)
• SafeDPO: A Simple Approach to Direct Preference Optimization with Enhanced Safety [57.14003339251827]
  We introduce a new algorithm called SafeDPO, which is designed to directly optimize the safety alignment objective in a single stage of policy learning.<n>As a result, it eliminates the need to fit separate reward and cost models or to sample from the language model during fine-tuning.<n>We demonstrate that SafeDPO achieves competitive performance compared to state-of-the-art safety alignment algorithms.
  arXiv  Detail & Related papers  (2025-05-26T14:50:01Z)
• Shape it Up! Restoring LLM Safety during Finetuning [66.46166656543761]
  Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks.<n>We propose dynamic safety shaping (DSS), a framework that uses fine-grained safety signals to reinforce learning from safe segments of a response while suppressing unsafe content.<n>We present STAR-DSS, guided by STAR scores, that robustly mitigates finetuning risks and delivers substantial safety improvements across diverse threats, datasets, and model families.
  arXiv  Detail & Related papers  (2025-05-22T18:05:16Z)
• Safety Modulation: Enhancing Safety in Reinforcement Learning through Cost-Modulated Rewards [23.15178050525514]
  Safe Reinforcement Learning (Safe RL) aims to train an RL agent to maximize its performance in real-world environments while adhering to safety constraints.<n>We propose a novel safe RL approach called Safety Modulated Policy Optimization (SMPO), which enables safe policy function learning.
  arXiv  Detail & Related papers  (2025-04-03T21:35:22Z)
• Probabilistic Shielding for Safe Reinforcement Learning [51.35559820893218]
  In real-life scenarios, a Reinforcement Learning (RL) agent must often also behave in a safe manner, including at training time.<n>We present a new, scalable method, which enjoys strict formal guarantees for Safe RL.<n>We show that our approach provides a strict formal safety guarantee that the agent stays safe at training and test time.
  arXiv  Detail & Related papers  (2025-03-09T17:54:33Z)
• SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning [10.844235123282056]
  Vision-language-action models (VLAs) show potential as generalist robot policies.<n>These models pose extreme safety challenges during real-world deployment, including the risk of harm to the environment, the robot itself, and humans.<n>We address this by exploring an integrated safety approach (ISA), systematically modeling safety requirements, then actively eliciting diverse unsafe behaviors.
  arXiv  Detail & Related papers  (2025-03-05T13:16:55Z)
• Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization [16.35399722653875]
  We propose Rectified Policy Optimization (RePO) to balance helpfulness and safety (harmlessness) in large language models (LLMs)<n>At the core of RePO is a policy update mechanism driven by rectified policy gradients, which penalizes the strict safety violation of every prompt, thereby enhancing safety across nearly all prompts.
  arXiv  Detail & Related papers  (2024-10-25T19:08:23Z)
• Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training [67.30423823744506]
  We introduce a novel approach, Decoupled Refusal Training (DeRTa), designed to empower LLMs to refuse compliance to harmful prompts at any response position.<n>DeRTa incorporates two novel components: (1) Maximum Likelihood Estimation with Harmful Response Prefix, which trains models to recognize and avoid unsafe content by appending a segment of harmful response to the beginning of a safe response, and (2) Reinforced Transition Optimization (RTO), which equips models with the ability to transition from potential harm to safety refusal consistently throughout the harmful response sequence.
  arXiv  Detail & Related papers  (2024-07-12T09:36:33Z)
• SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models [5.6874111521946356]
  Safety-aligned language models often exhibit fragile and imbalanced safety mechanisms.<n>We propose SafeInfer, a context-adaptive, decoding-time safety alignment strategy.<n>HarmEval is a novel benchmark for extensive safety evaluations.
  arXiv  Detail & Related papers  (2024-06-18T05:03:23Z)
• Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments [84.3830478851369]
  We propose a safe reinforcement learning approach that can jointly learn the environment and optimize the control policy. Our approach can effectively enforce hard safety constraints and significantly outperform CMDP-based baseline methods in system safe rate measured via simulations.
  arXiv  Detail & Related papers  (2022-09-29T20:49:25Z)

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.