Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs

• URL: http://arxiv.org/abs/2502.20968v1
• Date: Fri, 28 Feb 2025 11:31:27 GMT
• Title: Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
• Authors: Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu,
• Abstract summary: We conduct the first comprehensive assessment of role-play fine-tuning risks using RoleBench.<n>Experiments reveal that role-play fine-tuning leads to a noticeable decline in safety performance.<n>We propose Safety-Aware Role-Play Fine-Tuning (SaRFT), a novel method designed to balance role-playing capabilities and safety.
• Score: 73.09848497762667
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Role-playing enables large language models (LLMs) to engage users in immersive and personalized interactions, but it also introduces significant safety risks. Existing role-play fine-tuning techniques improve role adaptability but may degrade safety performance, particularly for villainous characters. In this work, we conduct the first comprehensive assessment of role-play fine-tuning risks by training 95 role-specific LLMs using RoleBench. Our experiments reveal that role-play fine-tuning leads to a noticeable decline in safety performance, with safety risks varying based on character traits. To tackle this challenge, we propose Safety-Aware Role-Play Fine-Tuning (SaRFT), a novel method designed to balance role-playing capabilities and safety. Extensive experiments on LLaMA-3-8B-Instruct, Gemma-2-9B-it, and Qwen2.5-7B-Instruct demonstrate that SaRFT consistently outperforms state-of-the-art baselines under both LoRA and full-parameter fine-tuning settings. Our findings highlight the necessity of role-adaptive safety measures and provide insights into mitigating role-specific safety risks in role-playing LLMs.

Related papers

• The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents [29.974647411289826]
  Large Language Models (LLMs) have made remarkable advances in role-playing dialogue agents, demonstrating their utility in character simulations.<n>It remains challenging for these agents to balance character portrayal utility with content safety because this essential character simulation often comes with the risk of generating unsafe content.<n>We propose a novel Adaptive Dynamic Multi-Preference (ADMP) method, which dynamically adjusts safety-utility preferences based on the degree of risk coupling.
  arXiv  Detail & Related papers  (2025-02-28T06:18:50Z)
• AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection [47.83354878065321]
  We propose AGrail, a lifelong guardrail to enhance agent safety.<n>AGrail features adaptive safety check generation, effective safety check optimization, and tool compatibility and flexibility.
  arXiv  Detail & Related papers  (2025-02-17T05:12:33Z)
• Internal Activation as the Polar Star for Steering Unsafe LLM Behavior [50.463399903987245]
  We introduce SafeSwitch, a framework that dynamically regulates unsafe outputs by monitoring and utilizing the model's internal states.<n>Our empirical results show that SafeSwitch reduces harmful outputs by over 80% on safety benchmarks while maintaining strong utility.
  arXiv  Detail & Related papers  (2025-02-03T04:23:33Z)
• SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models [75.67623347512368]
  We propose toolns, a comprehensive framework designed for conducting safety evaluations of MLLMs. Our framework consists of a comprehensive harmful query dataset and an automated evaluation protocol. Based on our framework, we conducted large-scale experiments on 15 widely-used open-source MLLMs and 6 commercial MLLMs.
  arXiv  Detail & Related papers  (2024-10-24T17:14:40Z)
• AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts [0.0]
  As Large Language Models (LLMs) and generative AI become more widespread, the content safety risks associated with their use also increase. We find a notable deficiency in high-quality content safety datasets and benchmarks that comprehensively cover a wide range of critical safety areas. To address this, we define a broad content safety risk taxonomy, comprising 13 critical risk and 9 sparse risk categories.
  arXiv  Detail & Related papers  (2024-04-09T03:54:28Z)
• ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding [89.0074567748505]
  We present reverse prompt contrastive decoding (ROSE), a simple-yet-effective method to boost the safety of existing instruction-tuned LLMs without any additional training. Experiments on 6 safety and 2 general-purpose tasks show that, our ROSE not only brings consistent and significant safety improvements (up to +13.8% safety score) upon 5 types of instruction-tuned LLMs, but also benefits the general-purpose ability of LLMs.
  arXiv  Detail & Related papers  (2024-02-19T06:58:42Z)
• Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment [62.898963074989766]
  We introduce Ditto, a self-alignment method for role-play. This method creates a role-play training set comprising 4,000 characters, surpassing the scale of currently available datasets by tenfold. We present the first comprehensive cross-supervision alignment experiment in the role-play domain.
  arXiv  Detail & Related papers  (2024-01-23T03:56:22Z)
• R-Judge: Benchmarking Safety Risk Awareness for LLM Agents [28.0550468465181]
  Large language models (LLMs) have exhibited great potential in autonomously completing tasks across real-world applications. This work addresses the imperative need for benchmarking the behavioral safety of LLM agents within diverse environments. We introduce R-Judge, a benchmark crafted to evaluate the proficiency of LLMs in judging and identifying safety risks given agent interaction records.
  arXiv  Detail & Related papers  (2024-01-18T14:40:46Z)
• Evil Geniuses: Delving into the Safety of LLM-based Agents [35.49857256840015]
  Large language models (LLMs) have revitalized in large language models (LLMs) This paper delves into the safety of LLM-based agents from three perspectives: agent quantity, role definition, and attack level.
  arXiv  Detail & Related papers  (2023-11-20T15:50:09Z)

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.