Decompose, Estimate, Select: Coverage-Aware Context Construction for Long-Form RAG

arXiv:2610.40314 · cs.IR · Submitted 2026-10-29 · Read on arXiv

cs.IR

Submitted: 2026-10-29

Updated: 2026-10-29

License: http://creativecommons.org/licenses/by/4.0/

The gist: Retrieval-augmented generation (RAG) grounds a language model's output in retrieved evidence, but for complex questions spanning multiple aspects of an information need…

Terminology

Abstract

Retrieval-augmented generation (RAG) grounds a language model's output in retrieved evidence, but for complex questions spanning multiple aspects of an information need, relevance-based retrieval may return redundant evidence while leaving some aspects unsupported. We propose a coverage-aware retrieval pipeline that decomposes queries into subquestions, ranks candidates with a coverage-trained bi-encoder, predicts a document, times,subquestion coverage matrix with a cross-encoder, and selects documents by greedy maximum-marginal coverage. On TREC RAG 2024, our approach improves α-nDCG@10, which rewards newly covered nuggets and discounts redundant evidence, from 0.625 to 0.702, approaching the 0.718 gold-nugget upper bound without sacrificing relevance. We then find that ground-truth oracle retrieval, despite substantially higher retrieval coverage, delivers no more nugget coverage to the answer than our estimated selection. This suggests that answer completeness depends not only on what evidence is retrieved, but also on how effectively the generator uses it. To address this, we introduce a grounded self-feedback loop in which the model identifies underused evidence from its first answer and generates again without gold supervision, raising V strict, the fraction of vital reference nuggets fully supported by the answer, by 0.086 over two passes while largely preserving faithfulness.

Related papers