大语言模型能理解文本中的歧义吗？一项开放世界问答的案例研究
Do LLMs Understand Ambiguity in Text? A Case Study in Open-world Question Answering
AI总结：
本文以开放域问答为案例，研究大语言模型对文本歧义的理解能力，并提出简单、无需训练的显式消歧方法以有效提升模型在歧义问答任务上的表现。
摘要：
自然语言中的歧义给用于开放域问答的大语言模型（LLMs）带来了重大挑战。LLMs 常常难以应对人类交流中固有的不确定性，从而导致误解、沟通错误、幻觉和带有偏见的回答。这显著削弱了它们在事实核查、问答、特征提取和情感分析等任务中的可用性。我们以开放域问答作为测试案例，比较了现成的和少样本的 LLM 性能，重点衡量显式消歧策略的影响。我们展示了简单、无需训练、基于词元级别的消歧方法如何被有效地用于提升 LLM 在歧义问答任务上的表现。我们通过实验展示了我们的发现，并讨论了关于 LLM 中歧义问题的最佳实践和更广泛的影响。
英文摘要：
Ambiguity in natural language poses significant challenges to Large Language Models (LLMs) used for open-domain question answering. LLMs often struggle with the inherent uncertainties of human communication, leading to misinterpretations, miscommunications, hallucinations, and biased responses. This significantly weakens their ability to be used for tasks like fact-checking, question answering, feature extraction, and sentiment analysis. Using open-domain question answering as a test case, we compare off-the-shelf and few-shot LLM performance, focusing on measuring the impact of explicit disambiguation strategies. We demonstrate how simple, training-free, token-level disambiguation methods may be effectively used to improve LLM performance for ambiguous question answering tasks. We empirically show our findings and discuss best practices and broader impacts regarding ambiguity in 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。
