Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability
Open Access
- 19 July 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 723-733
Abstract
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, 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, 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.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- LANCER: LLM Reranking for Nugget Coverage2026
- Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality2025
- A Workbench for Autograding Retrieve/Generate Systems2024
- On the Evaluation of Machine-Generated Reports2024
- Search Result Diversification Using Query Aspects as Bottlenecks2023
- ClueWeb22: 10 Billion Web Documents with Rich Information2022
- Reciprocal rank fusion outperforms condorcet and individual rank learning methods2009
- Novelty and diversity in information retrieval evaluation2008
- The Probability Ranking Principle RevisitedInformation Retrieval Journal, 2000
- The use of MMR, diversity-based reranking for reordering documents and producing summaries1998