提升长文本生成的覆盖度，让检索更全面。
Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability
- 用覆盖感知对比与蒸馏训练双编码器
- 相比基线覆盖度提升10%，不牺牲相关性
- 适合需要全面信息的长文本生成任务
长格式检索增强生成（RAG）面临覆盖度排序挑战，需确保相关事实片段被充分包含，以合成完整输出。本文提出CoveR，一种针对覆盖度感知检索优化的密集检索方法。CoveR采用基于覆盖度的对比与蒸馏目标进行双编码器训练，能捕捉信息需求的多样性。为训练CoveR，我们构建了SCOPE数据集，包含90K条来自Researchy Questions的训练对，其覆盖信号通过大模型生成的子问题可答性判断合成。实验表明，CoveR在不损失相关性的情况下，相较强基线提升了10%的片段覆盖度。消融研究验证了所提学习方法的有效性，证明CoveR在相关性与覆盖度间取得了更优权衡，对长格式RAG至关重要。
原文摘要 · Abstract (English)
Long-form Retrieval-Augmented Generation (RAG) brings the challenge of coverage-based ranking, because ranking methods must ensure the inclusion of comprehensive relevant nuggets (i.e., facts), which can thereby be synthesized into a comprehensive output. In this work, we propose CoveR (Our code is available at https://github.com/DylanJoo/CoveR ) a dense retrieval method optimized for coverage-aware retrieval scenarios. CoveR is a bi-encoder trained with the coverage-based contrastive and distillation objectives, which enables CoveR to capture diverse aspects of information needs. To train CoveR, we create the SCOPE dataset, (Our training data is available at https://huggingface.co/datasets/DylanJHJ/scope ) which comprises 90K training pairs from Researchy Questions with synthetic coverage signals augmented from sub-question answerability judgments generated by LLMs. Our empirical experiments show that CoveR enhances nugget coverage by 10\% over strong dense retrieval baselines without sacrificing its relevance-based retrieval capability. Further ablation studies validate the importance of our proposed learning method, showing that CoveR achieves a superior trade-off between relevance- and coverage-based ranking, which is essential for long-form RAG.
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。