LLM 法官在安全标准和危害类别上不一致地存在分歧
LLM Judges Inconsistently Disagree Across Safety Criteria and Harm Categories
AI总结：
本研究评估了自动法官在无参考设置下进行多维安全评估的一致性，发现大型语言模型在识别金融等受监管领域中机器生成建议的安全问题时不可靠，且不一致程度因安全标准、内容语言和风格而异，不同法官之间也存在高度分歧。
摘要：
我们评估了自动法官在无参考设置下进行多维安全评估的一致性。结果表明，大型语言模型在识别金融等受监管领域中机器生成建议的安全问题时不可靠，尽管它们在识别更明显的危险/有害内容（如暴力）时更为可靠。模型判断的不一致程度可能因所选安全标准而有显著差异，并且可能受内容语言及其语言风格的影响。最后，对于相同的输出，不同法官之间在领域、安全标准和语言上存在高度分歧。这些发现为使用LLM作为评估者的实践提供了新见解，并为从业者如何在实际场景中使用自动法官提供了若干建议。
英文摘要：
We evaluate the consistency of automated judges in conducting a multi-dimensional safety evaluation in a reference-free setup. Our results indicate that Large Language Models are unreliable judges in identifying safety issues related to machine-generated advice in regulated domains such as finance, although they are more reliable at identifying more overt forms of unsafe/harmful content such as violence. The degree of inconsistency in a model's judgments can vary significantly by the chosen safety criteria and can be impacted by the language of the content and its linguistic style as well. Finally, there is high disagreement among different judges for the same output, across domains, safety criteria, and languages. These findings provide new insights on the practice of using LLMs as evaluators and offer several recommendations for practitioners on how to use automated judges in practical scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
