检索增强生成中的归因-压缩前沿
The Attribution-Compression Frontier in Retrieval-Augmented Generation
浏览论文内容
中文总结 AI 辅助
本研究提出归因-压缩前沿概念，系统评估检索增强生成中不同压缩方法的引文归因质量，发现压缩器引文在摘要上精确度高但溯源到源文本时显著下降，且该差距依赖评估器，需人工校准。
中文摘要 AI 辅助
上下文压缩减少了检索增强生成中的生成器输入，但仅凭答案质量并不能刻画引文归因。我们在固定的生成器和主要蕴含评估器下，在ASQA和QASPER上比较了重排序、抽取式选择、抽象式摘要、令牌剪枝以及一种抽取-聚类-重写构造，测量了不同压缩方法和预算下的引文归因。在ASQA上，名义预算为0.25（实际压缩率为0.08）时，RECOMP风格压缩器的引文相对于其摘要的精确度为0.86，但在我们的重新归因协议下，相对于源文本片段的精确度仅为0.12。这些估计依赖于共享的NLI模型进行片段恢复和引文评分，且缺乏独立的人工校准。在ASQA上下文的二分之一到十分之一的名义预算范围内，抽取式选择的观测有根据精确度在0.43到0.49之间，而答案质量下降。对于相同的RECOMP设置，源恢复后的声明验证显示无支持率为0.88，而检查摘要时为0.17。这一差距在结构性地拒绝缺失来源之外依然存在，但仍依赖于评估器。一项包含200个问题的TRUE T5-XXL审计也发现，在固定和重新计算的源映射下均存在生成-有根据差距，但未建立人工校准的支持率。
英文摘要
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 under our re-attributability protocol. These estimates depend on a shared NLI model for span recovery and citation scoring and lack independent human calibration. Extractive selection's observed grounded precision ranges from 0.43 to 0.49 across nominal budgets from one-half to one-tenth of the ASQA context, while answer quality declines. For the same RECOMP setting, claim verification after source recovery yields an unsupported rate of 0.88 versus 0.17 when checking summaries. This gap persists beyond structural rejection of missing provenance, but remains evaluator-dependent. A 200-question TRUE T5-XXL audit also finds emitted--grounded gaps under both fixed and recomputed source mappings, without establishing human-calibrated support rates.
发表机构
- Center for Data Science（数据科学中心）
- New York University（纽约大学）
机构由 AI 辅助整理，请以论文原文为准。
