Efficient LLM Safety Evaluation through Multi-Agent Debate

• URL: http://arxiv.org/abs/2511.06396v1
• Date: Sun, 09 Nov 2025 14:06:55 GMT
• Title: Efficient LLM Safety Evaluation through Multi-Agent Debate
• Authors: Dachuan Lin, Guobin Shen, Zihao Yang, Tianrong Liu, Dongcheng Zhao, Yi Zeng,
• Abstract summary: We propose a cost-efficient multi-agent judging framework that employs Small Language Models (SLMs) through structured debates among critic, defender, and judge agents.<n>To rigorously assess safety judgments, we construct HAJailBench, a large-scale human-annotated jailbreak benchmark.<n>Our framework achieves agreement comparable to GPT-4o judges on HAJailBench while substantially reducing inference cost.
• Score: 18.818180932660294
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Safety evaluation of large language models (LLMs) increasingly relies on LLM-as-a-Judge frameworks, but the high cost of frontier models limits scalability. We propose a cost-efficient multi-agent judging framework that employs Small Language Models (SLMs) through structured debates among critic, defender, and judge agents. To rigorously assess safety judgments, we construct HAJailBench, a large-scale human-annotated jailbreak benchmark comprising 12,000 adversarial interactions across diverse attack methods and target models. The dataset provides fine-grained, expert-labeled ground truth for evaluating both safety robustness and judge reliability. Our SLM-based framework achieves agreement comparable to GPT-4o judges on HAJailBench while substantially reducing inference cost. Ablation results show that three rounds of debate yield the optimal balance between accuracy and efficiency. These findings demonstrate that structured, value-aligned debate enables SLMs to capture semantic nuances of jailbreak attacks and that HAJailBench offers a reliable foundation for scalable LLM safety evaluation.

Related papers

• PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks [7.252454104194306]
  Large language models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks.<n>Despite growing efforts in LLM safety research, existing evaluations are often fragmented, focused on isolated attack or defense techniques.<n>We introduce PandaGuard, a unified and modular framework that models LLM jailbreak safety as a multi-agent system comprising attackers, defenders, and judges.
  arXiv  Detail & Related papers  (2025-05-20T03:14:57Z)
• Investigating the Vulnerability of LLM-as-a-Judge Architectures to Prompt-Injection Attacks [0.0]
  Large Language Models (LLMs) are increasingly employed as evaluators (LLM-as-a-Judge) for assessing the quality of machine-generated text.<n>This paper investigates the vulnerability of LLM-as-a-Judge architectures to prompt-injection attacks.
  arXiv  Detail & Related papers  (2025-05-19T16:51:12Z)
• Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge [1.1666234644810893]
  Small models outperform larger ones in safety, suggesting that training and architecture may matter more than scale.<n>No model is fully robust to adversarial elicitation, with jailbreak attacks using low-resource languages or refusal suppression proving effective.
  arXiv  Detail & Related papers  (2025-04-10T16:00:59Z)
• LLM-Safety Evaluations Lack Robustness [58.334290876531036]
  We argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise.<n>We propose a set of guidelines for reducing noise and bias in evaluations of future attack and defense papers.
  arXiv  Detail & Related papers  (2025-03-04T12:55:07Z)
• SafeDialBench: A Fine-Grained Safety Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks [90.41592442792181]
  We propose a fine-grained benchmark SafeDialBench for evaluating the safety of Large Language Models (LLMs)<n>Specifically, we design a two-tier hierarchical safety taxonomy that considers 6 safety dimensions and generates more than 4000 multi-turn dialogues in both Chinese and English under 22 dialogue scenarios.<n> Notably, we construct an innovative assessment framework of LLMs, measuring capabilities in detecting, and handling unsafe information and maintaining consistency when facing jailbreak attacks.
  arXiv  Detail & Related papers  (2025-02-16T12:08:08Z)
• 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)
• Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks [23.782566331783134]
  We focus on 10 cutting-edge jailbreak strategies across three categories, 1525 questions from 61 specific harmful categories, and 13 popular LLMs. We adopt multi-dimensional metrics such as Attack Success Rate (ASR), Toxicity Score, Fluency, Token Length, and Grammatical Errors to thoroughly assess the LLMs' outputs under jailbreak. We explore the relationships among the models, attack strategies, and types of harmful content, as well as the correlations between the evaluation metrics, which proves the validity of our multifaceted evaluation framework.
  arXiv  Detail & Related papers  (2024-08-18T01:58:03Z)
• SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal [64.9938658716425]
  SORRY-Bench is a proposed benchmark for evaluating large language models' (LLMs) ability to recognize and reject unsafe user requests.<n>First, existing methods often use coarse-grained taxonomy of unsafe topics, and are over-representing some fine-grained topics.<n>Second, linguistic characteristics and formatting of prompts are often overlooked, like different languages, dialects, and more -- which are only implicitly considered in many evaluations.
  arXiv  Detail & Related papers  (2024-06-20T17:56:07Z)
• ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming [64.86326523181553]
  ALERT is a large-scale benchmark to assess safety based on a novel fine-grained risk taxonomy. It aims to identify vulnerabilities, inform improvements, and enhance the overall safety of the language models.
  arXiv  Detail & Related papers  (2024-04-06T15:01:47Z)
• SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models [107.82336341926134]
  SALAD-Bench is a safety benchmark specifically designed for evaluating Large Language Models (LLMs) It transcends conventional benchmarks through its large scale, rich diversity, intricate taxonomy spanning three levels, and versatile functionalities.
  arXiv  Detail & Related papers  (2024-02-07T17:33:54Z)

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.