Adaptive Query Performance Prediction for Retrieval-Augmented Generation: Bridging Retrieval Quality and Generation Relevance
ACM Transactions on Information Systems · 31.07.2026 · 44 (6) · 1-56
DOI: 10.1145/3827605 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 11.08.2026. Verfasst von Aparajita Sinha und 1 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Query Performance Prediction (QPP) estimates retrieval system effectiveness without relevance judgments, a challenge that intensifies in Retrieval-Augmented Generation (RAG) pipelines where retrieval quality directly shapes downstream answer quality. We introduce RAG-QPP , a retrieval-centric framework that predicts query difficulty from a 12-dimensional post-retrieval feature set combining semantic similarity, lexical, and score-distribution signals, extending beyond classical QPP measures (Clarity, WIG, and NQC). Unlike generator-dependent approaches that require model-internal signals such as perplexity or token-level uncertainty, RAG-QPP operates exclusively on post-retrieval features, remaining applicable to any black-box generator without modification. Random Forest, XGBoost, and LightGBM are evaluated across four retrieval paradigms (sparse, dense, hybrid, and late-interaction) on the MS MARCO Passage, MS MARCO Document, Natural Questions, and Robust04 datasets. Prediction accuracy is assessed via Pearson \( r \) , Spearman \(\rho\) , and Kendall \(\tau\) , with MRR@10 as the primary target and nDCG@10 and Average Precision (AP) as supplementary metrics. RAG-QPP achieves moderate but statistically significant correlations with ground-truth MRR@10 (Pearson \(r=0.6587\) in-domain; \(r=0.5332\) out-of-domain) without dataset-specific tuning. Predicted scores align with BART-large and LLaMA-3-8B generation quality across ROUGE-L, BERTScore-F1, and token-level F1 ( \(r\approx 0.22\) –0.48). QPP-guided adaptive retrieval yields consistent generation improvements, with the largest gains for low-effectiveness queries ( \(\Delta\) ROUGE-L \(=\,{+}0.057\) ), exceeding a learning-free adaptive baseline and confirming that the benefit derives from the learned retrieval-quality signal. Ablation confirms the dominance of semantic similarity features over traditional lexical QPP signals under neural retrieval. Random Forest leads in-domain while LightGBM generalizes best under distribution shift. RAG-QPP provides an interpretable, modular, and architecture-agnostic diagnostic layer for adaptive RAG systems. The implementation and associated resources are publicly available at https://github.com/APARAJITA1997/RAG_QPP_JH_2026 .
Zitieren
APA
Sinha, A., & Chakma, K. (2026). Adaptive Query Performance Prediction for Retrieval-Augmented Generation: Bridging Retrieval Quality and Generation Relevance. ACM Transactions on Information Systems, 44(6), 1-56. https://doi.org/10.1145/3827605
Vancouver
Sinha A, Chakma K. Adaptive Query Performance Prediction for Retrieval-Augmented Generation: Bridging Retrieval Quality and Generation Relevance. ACM Transactions on Information Systems. 2026;44(6):1-56. doi:10.1145/3827605
BibTeX
@article{Sinha2026,
author = {Sinha, Aparajita and Chakma, Kunal},
title = {Adaptive Query Performance Prediction for Retrieval-Augmented Generation: Bridging Retrieval Quality and Generation Relevance},
journal = {ACM Transactions on Information Systems},
year = {2026},
volume = {44},
number = {6},
pages = {1--56},
doi = {10.1145/3827605}
}
EUVIMED