Answer Presence Drives RAG Rewriting Gains

• URL: http://arxiv.org/abs/2606.05633v1
• Date: Thu, 04 Jun 2026 03:00:42 GMT
• Title: Answer Presence Drives RAG Rewriting Gains
• Abstract summary: Retrieval-augmented QA pipelines often route retrieved passages through an LLM emphrewriter before a smaller reader.<n>We ask whether that lift is causally driven by the gold answer string appearing in the rewritten context.
• Score: 21.554301305644156
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-augmented QA pipelines often route retrieved passages through an LLM \emph{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 \texttt{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-\texttt{[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.

Related papers

• Better Together: Complementary Query Rewriting Under a Strong RAG Baseline [0.03110995905282905]
  We compare four query-rewriting strategies (S1-S4) against two strong baselines (HyDE, Query2Doc)<n>Our headline result is that rewriting alone is at best competitive with a strong baseline, but combining methods yields outsized gains because different strategies fail on different questions.
  arXiv  Detail & Related papers  (2026-09-04T18:15:57Z)
• What Survives Into Context: A Diagnostic for Budget-Constrained Multi-Hop RAG and When Submodular Evidence Packing Improves It [0.0]
  We argue that document recall is the wrong quantity to optimize in a fixed reader-context budget.<n>We introduce answer-in-context, a diagnostic that measures whether a gold answer survives as a contiguous span in the packed reader context.<n>We map the scope of this win honestly: it requires the conjunction of (i) multi-hop complementary structure, (ii) retrieval that surfaces the evidence, (iii) a binding but not extreme budget, and (iv) a reader weak enough that evidence density, not reading capacity, is the bottleneck.
  arXiv  Detail & Related papers  (2026-07-01T10:12:15Z)
• Isolating LLM Alignment from Regex: Zero Coverage and Metric-Dependent Divergence Under Adversarial Mutation [51.56484100374058]
  Previous work found no measurable coverage gain from adding a live Gemini backend behind an active filter.<n>We introduce $L_5$-no-regex -- identical to $L_4$-real (Gemini-2.5-flash, token-budget cap, rate limit, output scrub) but with the nine-pattern filter disabled.<n>We evaluate it against adversarial probes across three sub-languages.
  arXiv  Detail & Related papers  (2026-06-12T18:54:24Z)
• Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing [51.56484100374058]
  Production LLM applications stack several defense families -- refusal-phrase filters, tokenbudget controls, model allowlists, rate limits, tool-registry authentication -- yetBAS benchmarks report a single aggregate coverage number.<n>We add four-LLM-Top-10-aware agents to a 21-agent baseline scanner and target a lattice of four synthetic LLM endpoints.
  arXiv  Detail & Related papers  (2026-06-01T19:39:25Z)
• Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering [44.82662196757139]
  We propose a lightweight, plug-in-ready process reward that replaces neural verifiers with a corpus-grounded signal from Wikipedia.<n>Across 30 (model, benchmark) cells spanning six instruction-tuned models, CorVer improves over the raw baseline for every cell.<n>It also outperforms four neural-verifier baselines in 18 of 20 cells under their feasible configurations, while training 4.8 to 8.4x faster.
  arXiv  Detail & Related papers  (2026-05-28T09:14:37Z)
• The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure [8.86745721473138]
  Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers.<n>We call this unfaithful capitulation (UC) and isolate it with a $2times 2$ latent-versus-behavioral framework that flip-rate metrics and single-turn probes both miss.
  arXiv  Detail & Related papers  (2026-05-27T20:41:08Z)
• Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Audit [0.30586855806896046]
  We adapt the classical paired sample-size calculation to quantization benchmarks.<n>The bound turns "how reliable is my quantization claim?" into a one-line budget.<n>We complement the bound with a five-line pre-registration template.
  arXiv  Detail & Related papers  (2026-05-25T07:13:35Z)
• StepGap: A Hybrid NLI-LLM Checker for Step-Level Evidence-Gap Detectionin Multi-Hop Question Answering [28.730693625995215]
  StepGap is a hybrid NLI-LLM decision tree that detects step-level evidence gaps in multi-hop QA.<n>Used as a typed GRPO process reward, StepGap improves Qwen2.5-7B-Instruct Exact Match from $32.1pm0.3$ to $35.4pm0.9$ across three seeds.
  arXiv  Detail & Related papers  (2026-05-23T20:57:19Z)
• MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks [68.78064578688809]
  MTR-Suite is a unified framework for auditing, synthesizing, and benchmarking retrieval.<n>It features: (1) MTR-Eval, an LLM-based auditor quantifying alignment gaps in previous benchmarks; (2) MTR-Pipeline, a multi-agent system using greedy clustering to generate high-fidelity dialogues at 1/400th human cost; and (3) MTR-Bench, a rigorous general-domain benchmark.
  arXiv  Detail & Related papers  (2026-05-20T05:26:35Z)
• Block-Wise Differentiable Sinkhorn Attention: Tail-Refinement Gradients with a Gap-Aware Dustbin Bridge [0.0]
  We study long-context balanced optimal transport attention on TPU hardware through a stopped-base, fixed-depth tail-refinement surrogate.<n>We provide a local surrogate-bias bound, an a posteriori bias certificate, and a projective contraction certificate for strictly positive active blocks.<n>On synthetic masked problems, the optimized matches exact autodiff of the same centered surrogate to within $10-5$--$10-10$.
  arXiv  Detail & Related papers  (2026-04-28T19:01:11Z)
• Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing [2.6382975801439836]
  LLMs edit text and code by autoregressively regenerating the full output, even when most tokens appear verbatim in the input.<n>We study Copy-as-Decode, a decoding-layer mechanism that recasts edit generation as structured decoding over a two-primitive grammar.
  arXiv  Detail & Related papers  (2026-04-20T12:29:53Z)
• PAR$^2$-RAG: Planned Active Retrieval and Reasoning for Multi-Hop Question Answering [57.89576196160413]
  Large language models (LLMs) remain brittle on multi-hop question answering (MHQA)<n>We propose textbfPlanned Active Retrieval and Reasoning RAG (PAR$2$-RAG), a two-stage framework that separates emphcoverage from emphcommitment.
  arXiv  Detail & Related papers  (2026-03-30T23:52:54Z)
• A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement Learning [46.81869577197105]
  A$2$Search is an annotation-free, end-to-end training framework to recognize and handle ambiguity.<n> Experiments on eight open-domain QA benchmarks demonstrate that A$2$Search achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-10-09T08:53:31Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.