arXiv 2502.085542025-02-12cs.HCcs.AI

促进对大型语言模型的适当依赖：解释、来源和不一致性的作用

Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies

Princeton University（普林斯顿大学）；Microsoft Research（微软研究院）

Sunnie S. Y. Kim, Jennifer Wortman Vaughan, Q. Vera Liao, Tania Lombrozo, Olga Russakovsky

备注：: CHI 2025. This version includes the appendix
DOI：: 10.1145/3706598.3714020

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究通过出声思考和对照实验（N=308），探究解释、来源和解释不一致性对用户依赖LLMs的影响，发现解释会增加依赖，而来源和解释不一致可减少对错误响应的依赖，为缓解过度依赖提供了依据。

摘要：

大型语言模型（LLMs）可能生成错误但流畅且有说服力的响应，增加用户将这些响应当作正确内容依赖的风险。缓解这种过度依赖是关键挑战。通过一项出声思考研究（参与者使用集成LLM的应用回答客观问题），我们确定了影响用户依赖的LLM响应特征：解释（回答的支持细节）、解释中的不一致性和来源。通过大规模、预注册的对照实验（N=308），我们分离并研究了这些特征对用户依赖、准确性等指标的影响。研究发现，解释的存在会增加对正确和错误响应的依赖；但提供来源或解释存在不一致时，对错误响应的依赖会减少。我们讨论了这些发现对促进适当依赖LLMs的意义。

英文摘要：

Large language models (LLMs) can produce erroneous responses that sound fluent and convincing, raising the risk that users will rely on these responses as if they were correct. Mitigating such overreliance is a key challenge. Through a think-aloud study in which participants use an LLM-infused application to answer objective questions, we identify several features of LLM responses that shape users' reliance: explanations (supporting details for answers), inconsistencies in explanations, and sources. Through a large-scale, pre-registered, controlled experiment (N=308), we isolate and study the effects of these features on users' reliance, accuracy, and other measures. We find that the presence of explanations increases reliance on both correct and incorrect responses. However, we observe less reliance on incorrect responses when sources are provided or when explanations exhibit inconsistencies. We discuss the implications of these findings for fostering appropriate reliance on LLMs.

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。

AI总结：

摘要：

英文摘要：

相关论文