Towards Comprehensive and Efficient Post Safety Alignment of Large Language Models via Safety Patching

• URL: http://arxiv.org/abs/2405.13820v1
• Date: Wed, 22 May 2024 16:51:07 GMT
• Title: Towards Comprehensive and Efficient Post Safety Alignment of Large Language Models via Safety Patching
• Authors: Weixiang Zhao, Yulin Hu, Zhuojun Li, Yang Deng, Yanyan Zhao, Bing Qin, Tat-Seng Chua,
• Abstract summary: textscSafePatching is a novel framework for comprehensive and efficient PSA. textscSafePatching achieves a more comprehensive and efficient PSA than baseline methods.
• Score: 77.36097118561057
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanisms, which can still be induced to generate unsafe responses, exhibit over-safety by rejecting safe user inputs, and fail to preserve general utility after safety alignment. To this end, we propose a novel post safety alignment (PSA) method to address these inherent and emerging safety challenges, including safety enhancement, over-safety mitigation, and utility preservation. In specific, we introduce \textsc{SafePatching}, a novel framework for comprehensive and efficient PSA, where two distinct safety patches are developed on the harmful data to enhance safety and mitigate over-safety concerns, and then seamlessly integrated into the target LLM backbone without compromising its utility. Extensive experiments show that \textsc{SafePatching} achieves a more comprehensive and efficient PSA than baseline methods. It even enhances the utility of the backbone, further optimizing the balance between being helpful and harmless in current aligned LLMs. Also, \textsc{SafePatching} demonstrates its superiority in continual PSA scenarios.

Related papers

• Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization [16.35399722653875]
  We propose textbfRectified Policy Optimization (RePO), which replaces the average safety constraint with stricter (per prompt) safety constraints. At the core of RePO is a policy update mechanism driven by rectified policy gradients, which penalizes the strict safety violation of every prompt. Our experiments on Alpaca-7B demonstrate that RePO improves the safety alignment and reduces the safety interference compared to baseline methods.
  arXiv  Detail & Related papers  (2024-10-25T19:08:23Z)
• Superficial Safety Alignment Hypothesis [8.297367440457508]
  We propose the Superficial Safety Alignment Hypothesis (SSAH), which posits that safety alignment should teach an otherwise unsafe model to choose the correct reasoning direction. We identify four types of attribute-critical components in safety-aligned large language models (LLMs) Our findings show that freezing certain safety-critical components 7.5% during fine-tuning allows the model to retain its safety attributes while adapting to new tasks.
  arXiv  Detail & Related papers  (2024-10-07T19:53:35Z)
• Nothing in Excess: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering [56.92068213969036]
  Safety alignment is indispensable for Large language models (LLMs) to defend threats from malicious instructions. Recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue. We propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns.
  arXiv  Detail & Related papers  (2024-08-21T10:01:34Z)
• SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models [5.6874111521946356]
  Safety-aligned language models often exhibit fragile and imbalanced safety mechanisms. We propose SafeInfer, a context-adaptive, decoding-time safety alignment strategy. HarmEval is a novel benchmark for extensive safety evaluations.
  arXiv  Detail & Related papers  (2024-06-18T05:03:23Z)
• Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations [19.132597762214722]
  Current alignment methods struggle with dynamic user intentions and complex objectives. We propose Safety Arithmetic, a training-free framework enhancing safety across different scenarios. Our experiments show that Safety Arithmetic significantly improves safety measures, reduces over-safety, and maintains model utility.
  arXiv  Detail & Related papers  (2024-06-17T17:48:13Z)
• Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning [57.84059344739159]
  "Shielding" is a popular technique to enforce safety inReinforcement Learning (RL) We propose a new permissibility-based framework to deal with safety and shield construction.
  arXiv  Detail & Related papers  (2024-05-29T18:00:21Z)
• Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications [69.13807233595455]
  Large language models (LLMs) show inherent brittleness in their safety mechanisms. This study explores this brittleness of safety alignment by leveraging pruning and low-rank modifications. We show that LLMs remain vulnerable to low-cost fine-tuning attacks even when modifications to the safety-critical regions are restricted.
  arXiv  Detail & Related papers  (2024-02-07T18:34:38Z)
• The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness [56.174255970895466]
  Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications. This paper presents Safety and Over-Defensiveness Evaluation (SODE) benchmark.
  arXiv  Detail & Related papers  (2023-12-30T17:37:06Z)
• SafetyBench: Evaluating the Safety of Large Language Models [54.878612385780805]
  SafetyBench is a comprehensive benchmark for evaluating the safety of Large Language Models (LLMs) It comprises 11,435 diverse multiple choice questions spanning across 7 distinct categories of safety concerns. Our tests over 25 popular Chinese and English LLMs in both zero-shot and few-shot settings reveal a substantial performance advantage for GPT-4 over its counterparts.
  arXiv  Detail & Related papers  (2023-09-13T15:56:50Z)

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.