Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning

• URL: http://arxiv.org/abs/2602.13562v1
• Date: Sat, 14 Feb 2026 02:37:36 GMT
• Title: Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
• Authors: Yanbo Wang, Minzheng Wang, Jian Liang, Lu Wang, Yongcan Yu, Ran He,
• Abstract summary: We propose an Adaptive Safe Context Learning (ASCL) framework to improve the reasoning given proper context.<n> ASCL formulates safety alignment as a multi-turn tool-use process, empowering the model to autonomously decide when to consult safety rules and how to generate the ongoing reasoning.
• Score: 35.52517435286337
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While reasoning models have achieved remarkable success in complex reasoning tasks, their increasing power necessitates stringent safety measures. For safety alignment, the core challenge lies in the inherent trade-off between safety and utility. However, prevailing alignment strategies typically construct CoT training data with explicit safety rules via context distillation. This approach inadvertently limits reasoning capabilities by creating a rigid association between rule memorization and refusal. To mitigate the safety-utility trade-off, we propose the Adaptive Safe Context Learning (ASCL) framework to improve the reasoning given proper context. ASCL formulates safety alignment as a multi-turn tool-use process, empowering the model to autonomously decide when to consult safety rules and how to generate the ongoing reasoning. Furthermore, to counteract the preference for rule consultation during RL, we introduce Inverse Frequency Policy Optimization (IFPO) to rebalance advantage estimates. By decoupling rule retrieval and subsequent reasoning, our method achieves higher overall performance compared to baselines.

Related papers

• Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety [59.01189713115365]
  We evaluate the impact of explicitly specifying extensive safety codes versus demonstrating them through illustrative cases.<n>We find that referencing explicit codes inconsistently improves harmlessness and systematically degrades helpfulness.<n>We propose CADA, a case-augmented deliberative alignment method for LLMs utilizing reinforcement learning on self-generated safety reasoning chains.
  arXiv  Detail & Related papers  (2026-01-12T21:08:46Z)
• 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)
• Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention [53.25106308403173]
  We show that existing methods overlook the unique significance of safe reasoning, undermining their trustworthiness and posing potential risks in applications if unsafe reasoning is accessible for and exploited by malicious users.<n>We propose Intervened Preference Optimization (IPO), an alignment method that enforces safe reasoning by substituting compliance steps with safety triggers and constructing pairs for preference learning with strong signals.
  arXiv  Detail & Related papers  (2025-09-29T07:41:09Z)
• RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards [55.76285458905577]
  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.
  arXiv  Detail & Related papers  (2025-06-09T13:20:04Z)
• Shape it Up! Restoring LLM Safety during Finetuning [65.75757313781104]
  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)
• SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning [51.78514648677898]
  We propose SAFER, a framework for Safety Alignment via eFficient Ex-Ante Reasoning.<n>Our approach instantiates structured Ex-Ante reasoning through initial assessment, rule verification, and path calibration.<n> Experiments on multiple open-source LLMs demonstrate that SAFER significantly enhances safety performance while maintaining helpfulness and response efficiency.
  arXiv  Detail & Related papers  (2025-04-03T16:07:38Z)
• Deliberative Alignment: Reasoning Enables Safer Language Models [64.60765108418062]
  We introduce Deliberative Alignment, a new paradigm that teaches the model safety specifications and trains it to explicitly recall and accurately reason over the specifications before answering.<n>We used this approach to align OpenAI's o-series models, and achieved highly precise adherence to OpenAI's safety policies, without requiring human-written chain-of-thoughts or answers.
  arXiv  Detail & Related papers  (2024-12-20T21:00:11Z)
• FAWAC: Feasibility Informed Advantage Weighted Regression for Persistent Safety in Offline Reinforcement Learning [7.888219789657414]
  Safe offline reinforcement learning aims to learn policies that maximize cumulative rewards while adhering to safety constraints.<n>Key challenge is balancing safety and performance, particularly when the policy encounters out-of-distribution states and actions.<n>We introduce Feasibility Informed Advantage Weighted Actor-Critic (FAWAC), a method that prioritizes persistent safety in constrained Markov decision processes.
  arXiv  Detail & Related papers  (2024-12-12T02:28:50Z)
• Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning [7.888219789657414]
  In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints.<n>We address these issues with a novel approach that begins by learning a conservatively safe policy through the use of Conditional Variational Autoencoders.<n>We frame this as a Constrained Reward-Return Maximization problem, wherein the policy aims to optimize rewards while complying with the inferred latent safety constraints.
  arXiv  Detail & Related papers  (2024-12-11T22:00:07Z)
• Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints [15.904640266226023]
  We design a safety model that performs credit assignment to assess contributions of partial state-action trajectories on safety. We derive an effective algorithm for optimizing a safe policy using the learned safety model. We devise a method to dynamically adapt the tradeoff coefficient between safety reward and safety compliance.
  arXiv  Detail & Related papers  (2024-05-05T17:27:22Z)
• SCPO: Safe Reinforcement Learning with Safety Critic Policy Optimization [1.3597551064547502]
  This study introduces a novel safe reinforcement learning algorithm, Safety Critic Policy Optimization. In this study, we define the safety critic, a mechanism that nullifies rewards obtained through violating safety constraints. Our theoretical analysis indicates that the proposed algorithm can automatically balance the trade-off between adhering to safety constraints and maximizing rewards.
  arXiv  Detail & Related papers  (2023-11-01T22:12:50Z)

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.