CogniBench：一个受法律启发的评估大型语言模型认知忠实度的框架与数据集
CogniBench: A Legal-inspired Framework and Dataset for Assessing Cognitive Faithfulness of Large Language Models
AI总结：
针对LLM认知性陈述的幻觉评估难题，本文受法律证据评估启发，提出严格评估框架与CogniBench数据集，并开发自动标注流水线构建大规模CogniBench-L数据集，以训练准确的幻觉检测器。
摘要：
忠实性幻觉是大型语言模型（LLM）生成的、不受提供给该LLM的上下文所支持的声明。由于缺乏评估标准，现有的基准测试专注于重述源材料的“事实性陈述”，却忽略了涉及从给定上下文进行推断的“认知性陈述”。因此，评估和检测认知性陈述的幻觉仍然具有挑战性。受法律领域证据评估方式的启发，我们设计了一个严格的框架来评估认知性陈述不同级别的忠实度，并引入了CogniBench数据集，在其中展示了富有洞察力的统计数据。为了跟上快速发展的LLM，我们进一步开发了一个易于在不同模型间扩展的自动标注流水线。这促成了大规模的CogniBench-L数据集，该数据集有助于训练针对事实性和认知性幻觉的准确检测器。我们在以下网址发布了我们的模型和数据集：https://github.com/FUTUREEEEEE/CogniBench
英文摘要：
Faithfulness hallucinations are claims generated by a Large Language Model (LLM) not supported by contexts provided to the LLM. Lacking assessment standards, existing benchmarks focus on "factual statements" that rephrase source materials while overlooking "cognitive statements" that involve making inferences from the given context. Consequently, evaluating and detecting the hallucination of cognitive statements remains challenging. Inspired by how evidence is assessed in the legal domain, we design a rigorous framework to assess different levels of faithfulness of cognitive statements and introduce the CogniBench dataset where we reveal insightful statistics. To keep pace with rapidly evolving LLMs, we further develop an automatic annotation pipeline that scales easily across different models. This results in a large-scale CogniBench-L dataset, which facilitates training accurate detectors for both factual and cognitive hallucinations. We release our model and datasets at: https://github.com/FUTUREEEEEE/CogniBench
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。
