MORSE：通过反向评分实现多上下文排序以进行证据保留压缩
MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression
- University of Virginia（弗吉尼亚大学）
- AfterQuery
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
MORSE通过逆向评分和压缩感知排序，解决上下文压缩对顺序敏感的问题，提升多跳问答中的证据保留和整体性能。
AI中文摘要：
基于似然的上下文压缩可以通过顺序评分来考虑跨上下文的冗余，但这使得压缩结果对上下文顺序敏感。我们表明，在未改变的压缩器下，相同上下文集合的不同排列可以产生显著不同的证据保留结果。我们将这种敏感性归因于信息抢占：早期部分相关的上下文可以吸收共享信息的信用，从而抑制后期更强证据载体的增量分数，并增加其被移除的风险。受控的成对交换干预直接支持了这一机制，表明证据优先排序显著提高了支持证据的存活率。为了解决这个问题，我们引入了MORSE，一种用于证据保留上下文排序的压缩感知方法。MORSE将共同的逆向查询-证据原则应用于单个上下文和压缩后的候选输出，利用前者构建证据优先锚点，并利用后者指导压缩感知的排列选择。在多跳问答基准、压缩程序、预算和评分模型中，MORSE始终优于静态逆向排序和计算匹配的随机搜索，在证据保留方面有所改进，并相应地在下游问答中带来整体改进。我们的代码可在https://github.com/tbn5pj/MORSE_code获取。
英文摘要：
Retrieval-augmented generation often relies on multiple retrieved contexts that contain substantial redundancy, motivating context compression to preserve useful information under limited input budgets. Likelihood-based compressors can account for cross-context redundancy through sequential scoring, but this makes evidence scores dependent on context order. We show that permuting the same contexts under an unchanged compressor can substantially change which supporting evidence survives compression. We attribute this sensitivity to information preemption: earlier, partially relevant contexts can absorb credit for shared information, reducing the incremental scores of later, stronger evidence and increasing its risk of removal. Controlled pair-swap interventions provide direct empirical support for this mechanism by showing that placing stronger evidence before overlapping, partially relevant contexts can improve its survival. Based on this insight, we introduce MORSE, a compression-aware method for evidence-preserving context ordering. MORSE uses reverse query likelihood to construct an evidence-first anchor and to evaluate compressed candidate outputs, enabling compression-aware selection among alternative permutations. Across multi-hop Question Answering (QA) benchmarks, compression procedures, budgets, and scoring models, MORSE improves evidence retention over reverse ordering and generally outperforms matched random search, with downstream QA gains. Our code is available at https://github.com/tbn5pj/MORSE_code
