Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations

• URL: http://arxiv.org/abs/2603.17305v1
• Date: Wed, 18 Mar 2026 03:00:42 GMT
• Title: Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
• Abstract summary: CRAFT is an alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks.<n>We evaluate CRAFT on multiple safety benchmarks using two strong reasoning models, Qwen3-4B-Thinking and R1-Distill-Llama-8B, where it consistently outperforms state-of-the-art defenses such as IPO and SafeKey.
• Score: 27.268778254622998
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike prior defenses that operate primarily at the output level, CRAFT aligns large reasoning models to generate safety-aware reasoning traces by explicitly optimizing objectives defined over the hidden state space. Methodologically, CRAFT integrates contrastive representation learning with reinforcement learning to separate safe and unsafe reasoning trajectories, yielding a latent-space geometry that supports robust, reasoning-level safety alignment. Theoretically, we show that incorporating latent-textual consistency into GRPO eliminates superficially aligned policies by ruling them out as local optima. Empirically, we evaluate CRAFT on multiple safety benchmarks using two strong reasoning models, Qwen3-4B-Thinking and R1-Distill-Llama-8B, where it consistently outperforms state-of-the-art defenses such as IPO and SafeKey. Notably, CRAFT delivers an average 79.0% improvement in reasoning safety and 87.7% improvement in final-response safety over the base models, demonstrating the effectiveness of hidden-space reasoning alignment.

Related papers

• Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model [50.29667251847595]
  We show that despite being larger in model size and stronger in safety capability, there exists an alignment gap between teacher and student language models.<n>We propose a BoN sampling method that attributes the unsafe behavior back to the base LLMs in the latent space.<n>In particular, across 7 teacher models and 6 student models of different classes and sizes, we show an average attack success rate (ASR) reduction of 28.2% in DAN, 31.3% in WildJailbreak and 35.4 % in StrongREJECT benchmarks.
  arXiv  Detail & Related papers  (2026-04-01T02:42:41Z)
• Evaluating and Enhancing the Vulnerability Reasoning Capabilities of Large Language Models [15.849480549367684]
  We propose DAGVul, a novel framework that models vulnerability reasoning as a Directed Acyclic Graph (DAG) generation task.<n>By further introducing Reinforcement Learning with Verifiable Rewards (RLVR), we align model reasoning trace with program-intrinsic logic.<n>Our framework improves the reasoning F1-score by an average of 18.9% over all the baselines.
  arXiv  Detail & Related papers  (2026-02-06T13:19:45Z)
• Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment [37.06683377953812]
  Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG.<n>We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the statistical stability of an ensemble.
  arXiv  Detail & Related papers  (2026-02-02T03:26:45Z)
• Think-Reflect-Revise: A Policy-Guided Reflective Framework for Safety Alignment in Large Vision Language Models [58.17589701432514]
  Think-Reflect-Revise (TRR) is a training framework designed to enhance the safety alignment of Large Vision Language Models (LVLMs)<n>We first build a Reflective Safety Reasoning (ReSafe) dataset with 5,000 examples that follow a think-reflect-revise process.<n>We then fine-tune the target model using the ReSafe dataset to initialize reflective behavior, and finally reinforce policy-guided reflection through reinforcement learning.
  arXiv  Detail & Related papers  (2025-12-08T03:46:03Z)
• SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge [51.634837361795434]
  SaFeR-CLIP reconciles safety and performance, recovering up to 8.0% in zero-shot accuracy over prior methods.<n>We also contribute NSFW-Caps, a new benchmark of 1,000 highly-aligned pairs for testing safety under distributional shift.
  arXiv  Detail & Related papers  (2025-11-20T19:00:15Z)
• SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models [66.71948519280669]
  Multimodal Large Reasoning Models (MLRMs) demonstrate impressive crossmodal reasoning but often amplify safety risks under adversarial prompts.<n> Existing defenses mainly act at the output level and do not constrain the reasoning process, leaving models to implicit risks.<n>We propose SaFeR-VLM, which integrates four components and supports dynamic and interpretable safety decisions beyond surface-level filtering.
  arXiv  Detail & Related papers  (2025-10-08T10:39:12Z)
• ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning [64.32925552574115]
  ARMOR is a large language model that analyzes jailbreak strategies and extracts the core intent.<n> ARMOR achieves state-of-the-art safety performance, with an average harmful rate of 0.002 and an attack success rate of 0.06 against advanced optimization-based jailbreaks.
  arXiv  Detail & Related papers  (2025-07-14T09:05:54Z)
• Circumventing Safety Alignment in Large Language Models Through Embedding Space Toxicity Attenuation [13.971909819796762]
  Large Language Models (LLMs) have achieved remarkable success across domains such as healthcare, education, and cybersecurity.<n>Embedding space poisoning is a subtle attack vector where adversaries manipulate the internal semantic representations of input data to bypass safety alignment mechanisms.<n>We propose ETTA, a novel framework that identifies and attenuates toxicity-sensitive dimensions in embedding space via linear transformations.
  arXiv  Detail & Related papers  (2025-07-08T03:01:00Z)
• Curriculum-Guided Antifragile Reinforcement Learning for Secure UAV Deconfliction under Observation-Space Attacks [6.367978467906828]
  Reinforcement learning policies are vulnerable to adversarial attacks in the observation space.<n>We propose an antifragile RL framework designed to adapt against curriculum of incremental adversarial perturbations.<n>Results show that the antifragile policy consistently outperforms standard and robust RL baselines.
  arXiv  Detail & Related papers  (2025-06-26T10:10:41Z)
• Improving LLM Safety Alignment with Dual-Objective Optimization [81.98466438000086]
  Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks.<n>We propose an improved safety alignment that disentangles DPO objectives into two components: (1) robust refusal training, which encourages refusal even when partial unsafe generations are produced, and (2) targeted unlearning of harmful knowledge.
  arXiv  Detail & Related papers  (2025-03-05T18:01:05Z)
• Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking [54.10710423370126]
  We propose Reasoning-to-Defend (R2D), a training paradigm that integrates a safety-aware reasoning mechanism into Large Language Models' generation process.<n>CPO enhances the model's perception of the safety status of given dialogues.<n>Experiments demonstrate that R2D effectively mitigates various attacks and improves overall safety, while maintaining the original performances.
  arXiv  Detail & Related papers  (2025-02-18T15:48:46Z)
• Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization [53.04697800214848]
  Adversarial Training (AT) is pivotal in fortifying the robustness of deep learning models. AT methods, relying on direct iterative updates for target model's defense, frequently encounter obstacles such as unstable training and catastrophic overfitting. We present a general proxy guided defense framework, LAST' (bf Learn from the Pbf ast)
  arXiv  Detail & Related papers  (2023-10-19T13:13:41Z)

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.