# 答案存在性驱动RAG重写增益

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-04 11:00
- AIHOT 分数：46
- AIHOT 链接：https://aihot.virxact.com/items/cmq6ci8g4075qsl5ipgivjuu7
- 原文链接：https://arxiv.org/abs/2606.05633

## AI 摘要

一项干预审计研究揭示了检索增强问答流程中重写器（rewriter）性能提升的因果机制：增益主要来自重写上下文中出现正确答案字符串，而非证据质量本身的改善。在Qwen2.5-7B、Qwen3.5-35B、GLM-4.7三个读者模型、HotpotQA和2WikiMultihopQA两个数据集上的十二组实验显示，从重写输出中移除答案跨度导致读者F1分数比长度匹配的安慰剂对照额外下降28至64点；向原无答案的重写内容前缀注入答案则在10/12组合中带来0.7至9.7点的F1提升。传统单[MASK]探针检测法存在脆弱性——在2Wiki数据集上报告+4.12 F1“非泄漏残差”，但改用四种替代哨兵后结果翻转至-3.33至-7.81 F1，且其中三种未通过等价检验。

## 正文

Retrieval-augmented QA pipelines often route retrieved passages through an LLM rewriter before a smaller reader, lifting F1 by tens of points on multi-hop benchmarks; this gain is typically credited to improved evidence quality. We ask whether that lift is causally driven by the gold answer string appearing in the rewritten context rather than by curation per se, using a controlled intervention audit. For each rewritten context we re-run the reader after one of four controlled edits to the compile output: removing the gold answer span, replacing a length-matched random non-answer span (placebo), or injecting the gold into rewrites where it was absent (at the prefix or at a midpoint sentence boundary). Across twelve completed (cell, baseline) intervention runs spanning three reader families (Qwen2.5-7B, Qwen3.5-35B, GLM-4.7), two datasets (HotpotQA, 2WikiMultihopQA), and three compiler arrangements (MA-only, MB-only, MA+verify), removing the gold answer drops reader F1 by 28 to 64 points beyond the length-matched placebo on paired answer-in-compile strata, and prepending the gold into rewrites that lacked it raises F1 by +0.7 to +9.7 points in 10 of 12 (cell, baseline) combinations. A companion five-sentinel audit shows the conventional single-[MASK] probe is itself sentinel-fragile: on 2Wiki it reports a +4.12~F1 ``non-leakage residual'' that flips to -3.33 to -7.81~F1 under four alternative sentinels and fails an equivalence test for three of those four (1/4~pass). We do not propose a new rewriter or mitigation; we release the intervention runner and the sentinel panel so that other rewriter-gain claims can be tested against the same standard.