幻觉排行榜——一项衡量大语言模型幻觉问题的开放举措
The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models
AI总结：
针对大语言模型易产生幻觉的问题，本文推出开放的Hallucinations Leaderboard，通过覆盖多任务、多维度的综合基准量化对比各模型的幻觉倾向，为相关人员选择可靠模型提供参考。
摘要：
大语言模型（LLMs）凭借其理解和生成类人文本的卓越能力，彻底改变了自然语言处理（NLP）领域的格局。然而，这类模型容易产生“幻觉”——即与事实真相或输入上下文不相符的输出。本文推出了Hallucinations Leaderboard（幻觉排行榜），这是一项用于量化衡量并对比各模型产生幻觉倾向的开放计划。该排行榜采用一套全面的基准测试，聚焦幻觉的不同维度（如事实准确性和忠实度），覆盖问答、摘要生成、阅读理解等多种任务。我们的分析揭示了不同模型的性能表现，可为研究人员和从业者选择最可靠的模型用于其应用场景提供参考。
英文摘要：
Large Language Models (LLMs) have transformed the Natural Language Processing (NLP) landscape with their remarkable ability to understand and generate human-like text. However, these models are prone to ``hallucinations'' -- outputs that do not align with factual reality or the input context. This paper introduces the Hallucinations Leaderboard, an open initiative to quantitatively measure and compare the tendency of each model to produce hallucinations. The leaderboard uses a comprehensive set of benchmarks focusing on different aspects of hallucinations, such as factuality and faithfulness, across various tasks, including question-answering, summarisation, and reading comprehension. Our analysis provides insights into the performance of different models, guiding researchers and practitioners in choosing the most reliable models for their applications.
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。
