提出新框架，让AI能精准回答多个答案的复杂问题。
Inter-Passage Verification for Multi-evidence Multi-answer QA
- 先广搜证据段落，再独立生成答案，最后跨段验证真伪。
- 在两个数据集上平均F1提升11.17%，多证据题效果更显著。
- 适合需要综合多份资料才能答对的复杂问答场景。
多答案问答（Multi-answer QA）要求系统能识别并生成多个有效答案，这对现有基于检索增强生成的QA系统构成挑战，因其难以同时检索和整合大量证据段落。为此，本文提出新框架RI²VER：检索增强的独立阅读与跨段验证。该框架先检索大量段落，对每段独立生成初始高召回率但含噪声的答案集合；随后引入跨段验证流程，通过生成验证问题、获取额外证据、进行跨段合成验证，逐个确认候选答案的有效性。在QAMPARI和RoMQA数据集上的评估表明，该框架在不同模型规模下均显著优于现有基线，平均F1得分提升11.17%。进一步分析证实，该跨段验证机制特别有助于需多证据融合的复杂问题。
原文摘要 · Abstract (English)
Multi-answer question answering (QA), where questions can have many valid answers, presents a significant challenge for existing retrieval-augmented generation-based QA systems, as these systems struggle to retrieve and then synthesize a large number of evidence passages. To tackle these challenges, we propose a new multi-answer QA framework -- Retrieval-augmented Independent Reading with Inter-passage Verification (RI$^2$VER). Our framework retrieves a large set of passages and processes each passage individually to generate an initial high-recall but noisy answer set. Then we propose a new inter-passage verification pipeline that validates every candidate answer through (1) Verification Question Generation, (2) Gathering Additional Evidence, and (3) Verification with inter-passage synthesis. Evaluations on the QAMPARI and RoMQA datasets demonstrate that our framework significantly outperforms existing baselines across various model sizes, achieving an average F1 score improvement of 11.17%. Further analysis validates that our inter-passage verification pipeline enables our framework to be particularly beneficial for questions requiring multi-evidence synthesis.
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。