mlsanityData to 7 Oct 2026

Your Retriever Already Knows: Distribution-Shape QPP for RAG Retrieval Sufficiency

arXiv 2609.11646 ↗First posted 10 Sep 2026cs.IRcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Standard Retrieval-Augmented Generation (RAG) pipelines often provide no reliable inference-time signal of whether retrieval succeeded; on ambiguous or out-of-scope queries, generation may then hallucinate. Motivated by a Czech nuclear-regulator deployment where data sensitivity precludes third-party LLM APIs, we compare three Query Performance Prediction (QPP) paradigms for retrieval sufficiency in RAG: score-based features, a content-based LLM judge, and a hybrid. On the eight ViDoRe vision domains (14,514 queries), our 24 non-lexical features (GeneralQPP; 15 distribution-shape, 5 query-surface, 4 global) reach a weighted-average AUROC of 0.856 at 2 ms per query, ahead of a classic-QPP literature pool (Classic Full, 0.835) and well above a local Qwen3.5 LLM judge (0.649, +0.207 gap; ~3000× faster and cheaper per query). Adding the LLM judgment as one feature (hybrid) matches S1 on ViDoRe (0.863) but gains a statistically significant edge on S'UJB (AUROC 0.911 at Hit@5, adversarial-detection 0.954; 1,510 queries, 500 synthetic adversarial), at LLM latency. Rankings agree across datasets (Spearman ρ = 0.90). Under Leave-One-Domain-Out, S1 drops to 0.706; a 13-feature LODO-stepwise subset (S1-Lean) recovers to 0.719 (+0.032 over the literature pool).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 5 of its 21 references that are in the map. First posted on arXiv 10 Sep 2026.

Builds on

5 of 21 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 4

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2024ColPali: Efficient Document Retrieval with Vision Language Modelscited by 190
  3. 2023Query Performance Prediction for Neural IR: Are We There Yet?cited by 5
  4. 2025Uncovering the Limitations of Query Performance Prediction: Failures, Insights, and Implications for Selective Query Processingcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines
  2. 2025QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors
  3. 2024Toward Optimal Search and Retrieval for RAG
  4. 2026Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs
  5. 2026RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems
  6. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  7. 2026RAQG-QPP: Query Performance Prediction with Retrieved Query Variants and Retrieval Augmented Query Generation
  8. 2026One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAG