用多轮对话增强AI对高风险系统的隐患识别能力
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis
- 设计多智能体对话框架，通过多轮交互提升隐患识别
- 对抗辩论与建设性讨论均优于单次推理，准确率显著提升
- 适合关注AI安全与复杂系统风险评估的研究者
高风险领域如工业过程控制、自动驾驶和安全关键系统需要可靠的隐患识别。尽管大语言模型在自动化安全分析方面展现潜力，但单次、单一推理方式脆弱且缺乏工程师常用的自我修正与上下文优化能力。本文提出HAZDIAL框架，研究结构化代理对话（多智能体、多轮交互）是否能提升基于NLP的隐患识别质量。系统比较了对抗辩论与建设性讨论两种对话模式，并提出基于算法的代理交互优化策略。所有配置在精心构建的黄金数据集上进行评估，采用标准分类指标（准确率、精确率、召回率、F1）及新型对话评估指标。该工作推进了对话系统、多智能体推理与AI安全的交叉研究，为对话驱动的安全分析提供了实证支持。
原文摘要 · Abstract (English)
Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems, demand reliable hazard identification. While large language models (LLMs) have shown promise in automating safety analysis tasks, single-turn, monolithic inference is brittle: it lacks the self-correction, deliberation, and contextual refinement that safety engineers apply iteratively. In this paper, we introduce HAZDIAL, a framework that investigates whether structured agentic dialogue-multi-agent, multi-turn interactions improves the quality of NLP- based hazard identification over single-pass baselines. We systematically compare two dialogue modalities: adversarial debate and constructive discussion, and propose an algorithm-based agentic interaction optimization. We evaluate all configurations against a curated golden dataset using standard classification metrics (accuracy, precision, recall, F1) and novel dialogue metrics. This work advances the intersection of dialogue systems, multi-agent reasoning, and AI safety, providing an empirical evidence for dialogue-driven hazard analysis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。