通过弱监督提升长文本问答中的背景信息检索能力。
Retrieving Contextual Information for Long-Form Question Answering using Weak Supervision
- 利用弱监督技术优化检索模型，聚焦问题背景信息而非直接答案。
- 在ASQA数据集上，相关页面召回率提升14.7%，答案可信度提高12.5%。
- 生成的答案更可能预判后续问题，适合对话式问答场景。
长文本问答（LFQA）旨在为用户问题生成深入回答，提供超出直接答案的相关背景信息。然而，现有检索器通常只优化与问题直接相关的知识，忽略了上下文信息。此外，相关上下文的训练数据稀缺。为此，我们提出并比较了多种弱监督技术，用于优化上下文信息的检索。实验表明，在ASQA数据集上，端到端问答性能得到提升。更重要的是，随着更多上下文信息被检索，相关页面召回率提高了14.7%，生成答案的可信度提升了12.5%。最后，我们在对话式问答数据集上验证发现，长文本回答常能预见潜在的后续问题。
原文摘要 · Abstract (English)
Long-form question answering (LFQA) aims at generating in-depth answers to end-user questions, providing relevant information beyond the direct answer. However, existing retrievers are typically optimized towards information that directly targets the question, missing out on such contextual information. Furthermore, there is a lack of training data for relevant context. To this end, we propose and compare different weak supervision techniques to optimize retrieval for contextual information. Experiments demonstrate improvements on the end-to-end QA performance on ASQA, a dataset for long-form question answering. Importantly, as more contextual information is retrieved, we improve the relevant page recall for LFQA by 14.7% and the groundedness of generated long-form answers by 12.5%. Finally, we show that long-form answers often anticipate likely follow-up questions, via experiments on a conversational QA dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。