迈向长上下文幻觉检测
Towards Long Context Hallucination Detection
AI总结：
本文构建了专门用于长上下文幻觉检测的数据集，并提出一种基于分解和聚合机制的新架构，使BERT等预训练编码器能有效处理长上下文并检测幻觉，在多项指标上超越同类模型及LLM模型且推理更快。
摘要：
大型语言模型（LLMs）在各种任务中表现出卓越的性能。然而，它们容易出现上下文幻觉，生成与给定上下文不一致或无根据的信息。尽管许多研究调查了LLMs中的上下文幻觉，但在长上下文输入中解决此问题仍是一个开放问题。在这项工作中，我们通过构建一个专门为长上下文幻觉检测设计的数据集，迈出了解决该问题的第一步。此外，我们提出了一种新颖的架构，使预训练编码器模型（如BERT）能够处理长上下文，并通过分解和聚合机制有效检测上下文幻觉。我们的实验结果表明，所提出的架构在各项指标上显著优于相似规模的先前模型以及基于LLM的模型，同时提供更快的推理速度。
英文摘要：
Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. However, they are prone to contextual hallucination, generating information that is either unsubstantiated or contradictory to the given context. Although many studies have investigated contextual hallucinations in LLMs, addressing them in long-context inputs remains an open problem. In this work, we take an initial step toward solving this problem by constructing a dataset specifically designed for long-context hallucination detection. Furthermore, we propose a novel architecture that enables pre-trained encoder models, such as BERT, to process long contexts and effectively detect contextual hallucinations through a decomposition and aggregation mechanism. Our experimental results show that the proposed architecture significantly outperforms previous models of similar size as well as LLM-based models across various metrics, while providing substantially faster inference.
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。
