From Shallow to Deep: Pinning Semantic Intent via Causal GRPO

• URL: http://arxiv.org/abs/2603.02675v1
• Date: Tue, 03 Mar 2026 07:02:20 GMT
• Title: From Shallow to Deep: Pinning Semantic Intent via Causal GRPO
• Abstract summary: We propose Two-Stage Causal-GRPO, a framework designed to achieve intent pinning.<n>We show that TSC-GRPO significantly outperforms baselines in defending against jailbreak attacks while preserving general utility.
• Score: 40.89749712474356
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models remain vulnerable to adversarial prefix attacks (e.g., ``Sure, here is'') despite robust standard safety. We diagnose this vulnerability as Shallow Safety Alignment, stemming from a pathology we term semantic representation decay: as the model generates compliant prefixes, its internal malicious intent signal fades. To address this, we propose Two-Stage Causal-GRPO (TSC-GRPO), a framework designed to achieve intent pinning. First, grounded in causal identifiability theory, we train a causal intent probe to disentangle invariant intent from stylistic perturbations. Second, we internalize this causal awareness into the policy via Group Relative Policy Optimization. By employing a cumulative causal penalty within ``fork-in-the-road'' training scenarios, we force the model to learn that accumulating harmful tokens monotonically decreases reward, enabling robust late-stage refusals. Experiments show that TSC-GRPO significantly outperforms baselines in defending against jailbreak attacks while preserving general utility.

Related papers

• Optimizing Against Safety Representations: Activation-Guided Adversarial Suffixes and the Geometry of Refusal [3.441021278275805]
  Behavioral alignment in large language models often masks fragile internal safety representations.<n>We study adversarial suffix attacks as a probe of representational alignment.<n>We find that suppressing refusal globally across all layers and positions is more effective than targeting a single layer-position pair.
  arXiv  Detail & Related papers  (2026-07-09T19:21:29Z)
• TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning [60.68349524623048]
  Decompositional jailbreaks pose a critical threat to large language models.<n>We present TwinGate, a stateful dual-encoder defense framework.<n>We construct a comprehensive dataset of over 3.62 million instructions spanning 8,600 distinct malicious intents.
  arXiv  Detail & Related papers  (2026-04-30T13:44:01Z)
• Sleeper Cell: Injecting Latent Malice Temporal Backdoors into Tool-Using LLMs [0.0]
  Openweight Large Language Models (LLMs) have democratized agentic AI, yet finetuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance.<n>This creates a risk where third-party models are incorporated without strong behavioral guarantees.<n>We show that poisoned models maintain state-of-the-art performance on benign tasks, incentivizing their adoption.
  arXiv  Detail & Related papers  (2026-03-02T22:01:08Z)
• Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment [13.463606100715504]
  Large language models are vulnerable to attacks that disguise harmful intent.<n>This vulnerability stems from shallow alignment mechanisms that lack deep reasoning.<n>We propose enhancing alignment through reasoning-aware post-training.
  arXiv  Detail & Related papers  (2026-02-24T20:30:51Z)
• 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)
• Probing the Robustness of Large Language Models Safety to Latent Perturbations [30.16804362984161]
  Safety alignment is a key requirement for building reliable Artificial General Intelligence.<n>We observe that minor latent shifts can still trigger unsafe responses in aligned models.<n>We introduce Layer-wise Adversarial Patch Training(LAPT), a fine-tuning strategy that injects controlled perturbations into hidden representations during training.
  arXiv  Detail & Related papers  (2025-06-19T07:03:05Z)
• Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs [83.11815479874447]
  We propose a novel jailbreak attack framework, inspired by cognitive decomposition and biases in human cognition.<n>We employ cognitive decomposition to reduce the complexity of malicious prompts and relevance bias to reorganize prompts.<n>We also introduce a ranking-based harmfulness evaluation metric that surpasses the traditional binary success-or-failure paradigm.
  arXiv  Detail & Related papers  (2025-05-03T05:28:11Z)
• 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)
• Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions [50.40122190627256]
  We introduce POATE, a novel jailbreak technique that harnesses contrastive reasoning to provoke unethical responses.<n>PoATE crafts semantically opposing intents and integrates them with adversarial templates, steering models toward harmful outputs with remarkable subtlety.<n>To counter this, we propose Intent-Aware CoT and Reverse Thinking CoT, which decompose queries to detect malicious intent and reason in reverse to evaluate and reject harmful responses.
  arXiv  Detail & Related papers  (2025-01-03T15:40:03Z)
• Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing [107.97160023681184]
  Aligned large language models (LLMs) are vulnerable to jailbreaking attacks. We propose SEMANTICSMOOTH, a smoothing-based defense that aggregates predictions of semantically transformed copies of a given input prompt.
  arXiv  Detail & Related papers  (2024-02-25T20:36:03Z)

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.