面向文本摘要的幻觉多样性感知主动学习
Hallucination Diversity-Aware Active Learning for Text Summarization
AI总结：
本文提出首个缓解LLM幻觉的主动学习框架HADAS，通过从语义框架、话语和内容可验证性度量细粒度幻觉并选择多样化样本标注，在三个数据集上验证了其高效减轻文本摘要幻觉的效果。
摘要：
大型语言模型（LLMs）已表现出生成幻觉输出的倾向，即事实错误或缺乏依据的文本。现有缓解幻觉的方法通常需要昂贵的人工标注来识别和纠正LLM输出中的幻觉。此外，这些方法大多只关注特定类型的幻觉，例如实体或词元错误，这限制了它们在处理LLM输出中表现出的各类幻觉时的有效性。据我们所知，本文提出了首个用于缓解LLM幻觉的主动学习框架，以减少所需的高成本幻觉人工标注。通过在文本摘要中从语义框架、话语和内容可验证性方面的错误来度量细粒度幻觉，我们提出了幻觉多样性感知采样（HAllucination Diversity-Aware Sampling，HADAS），在用于LLM微调的主动学习中选择多样化的幻觉进行标注。在三个数据集和不同骨干模型上的大量实验证明了我们的方法在有效且高效地减轻LLM幻觉方面的优势。
英文摘要：
Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, most of these methods focus on a specific type of hallucination, e.g., entity or token errors, which limits their effectiveness in addressing various types of hallucinations exhibited in LLM outputs. To our best knowledge, in this paper we propose the first active learning framework to alleviate LLM hallucinations, reducing costly human annotations of hallucination needed. By measuring fine-grained hallucinations from errors in semantic frame, discourse and content verifiability in text summarization, we propose HAllucination Diversity-Aware Sampling (HADAS) to select diverse hallucinations for annotations in active learning for LLM finetuning. Extensive experiments on three datasets and different backbone models demonstrate advantages of our method in effectively and efficiently mitigating LLM hallucinations.
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。
