Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Information Retrieval | BEIR | SciFact0.714 | 120 | |
| Nugget Coverage Reranking | NeuCLIR ReportGen 2024 (test) | -- | 18 | |
| Nugget-based retrieval | CRUX Multi-News | Precision@1038 | 14 | |
| Nugget-based retrieval | CRUX DUC04 | Precision@1069.4 | 14 |