SOURCE-LINKED INTELLIGENCE

The Attribution-Compression Frontier in Retrieval-Augmented Generation

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Context compression reduces generator input in retrieval-augmented generation, but answer quality alone does not characterize citation attribution. We measure citation attribution across compression methods and budgets, comparing reranking, extractive selection, abstractive summarization, token pruning, and an extract-cluster-rewrite construction on ASQA and QASPER under a fixed generator and primary entailment evaluator. On ASQA at a nominal 0.25 budget (achieved compression 0.08), a RECOMP-style compressor's citations score 0.86 precision against its summaries but 0.12 against source spans u

Read original source ↗ Open in workspace

recordType: paper
region: Global

Evidence & attribution

arXiv · AI, language, vision and robotics · 2026-09-13T02:49:06.000Z

First collected: 2026-09-20T12:41:04.663Z. This is not the publication date.