arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.17073cs.CL
收藏

通过粗粒度答案分解增强长文档理解中的事后归因

Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition

Adobe Research(奥多比研究院)

Pritika Ramu, Koustava Goswami, Apoorv Saxena, Balaji Vasan Srinivasan

AI总结:

本文针对长文档问答中的事后归因问题,提出基于模板上下文学习和负采样的粗粒度答案事实分解方法,并系统评估其对检索式和LLM归因方法的提升效果。

摘要:

准确地将答案文本归因到其源文档对于构建可靠的问答系统至关重要。然而,长文档的归因问题在很大程度上仍未得到探索。事后归因系统旨在将答案文本映射回源文档,但这种映射的粒度尚未得到解决。此外,一个关键问题随之而来:究竟应该归因什么?这涉及识别答案中需要依据支撑的具体信息单元。在本文中,我们提出并研究了一种用于归因的生成答案事实分解新方法,采用基于模板的上下文学习。为实现这一目标,我们利用问题并在少样本上下文学习过程中引入负采样来进行分解。该方法增强了对抽取式和生成式答案的语义理解。我们通过对各种归因方法进行全面检验来考察答案分解的影响,这些方法涵盖从基于检索的技术到基于大语言模型的归因器。

英文摘要:

Accurately attributing answer text to its source document is crucial for developing a reliable question-answering system. However, attribution for long documents remains largely unexplored. Post-hoc attribution systems are designed to map answer text back to the source document, yet the granularity of this mapping has not been addressed. Furthermore, a critical question arises: What exactly should be attributed? This involves identifying the specific information units within an answer that require grounding. In this paper, we propose and investigate a novel approach to the factual decomposition of generated answers for attribution, employing template-based in-context learning. To accomplish this, we utilize the question and integrate negative sampling during few-shot in-context learning for decomposition. This approach enhances the semantic understanding of both abstractive and extractive answers. We examine the impact of answer decomposition by providing a thorough examination of various attribution approaches, ranging from retrieval-based techniques to LLM-based attributors.

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。

↑