RAQG-QPP: Query Performance Prediction with Retrieved Query Variants and Retrieval Augmented Query Generation

• URL: http://arxiv.org/abs/2604.27244v1
• Date: Wed, 29 Apr 2026 22:31:56 GMT
• Title: RAQG-QPP: Query Performance Prediction with Retrieved Query Variants and Retrieval Augmented Query Generation
• Abstract summary: We propose to make use of queries retrieved from a log of past queries as QVs to be subsequently used for QPP.<n>In addition to directly applying retrieved QVs in QPP, we further propose to leverage large language models (LLMs) to generate QVs conditioned on the retrieved QVs.
• Score: 24.439170886636788
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Query Performance Prediction (QPP) estimates the retrieval quality of ranking models without the use of any human-assessed relevance judgements, and finds applications in query-specific selective decision making to improve overall retrieval effectiveness. Although unsupervised QPP approaches are effective for lexical retrieval models, they usually perform weaker for neural rankers. Recent work shows that leveraging query variants (QVs), i.e., queries with potentially similar information needs to a given query, can enhance unsupervised QPP accuracy. However, existing QV-based prediction methods rely on query variants generated by term expansion of the input query, which is likely to yield incoherent, hallucinatory and off-topic QVs. In this paper, we propose to make use of queries retrieved from a log of past queries as QVs to be subsequently used for QPP. In addition to directly applying retrieved QVs in QPP, we further propose to leverage large language models (LLMs) to generate QVs conditioned on the retrieved QVs, thus mitigating the limitation of relying only on existing queries in a log. Experiments on TREC DL'19 and DL'20 show that QPP enhanced with RAQG outperform the best-performing existing QV-based prediction approach by as much as 30% on neural ranking models such as MonoT5.

Related papers

• Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines [48.34524144147475]
  Large Language Models (LLMs) have made query reformulation ubiquitous in modern retrieval and Retrieval-Augmented Generation (RAG) pipelines.<n>We investigate Query Performance Prediction (QPP) as a mechanism for variant selection across ad-hoc retrieval and end-to-end RAG.
  arXiv  Detail & Related papers  (2026-04-24T15:36:40Z)
• VQPP: Video Query Performance Prediction Benchmark [22.214338497366082]
  We propose the first benchmark for video query performance prediction (VQPP)<n>VQPP contains a total of 56K text queries and 51K videos, and comes with official training, validation and test splits.<n>We explore multiple pre-retrieval and post-retrieval performance predictors, creating a representative benchmark for future exploration of QPP in the video domain.
  arXiv  Detail & Related papers  (2026-02-19T20:32:25Z)
• Breaking Flat: A Generalised Query Performance Prediction Evaluation Framework [10.378957672522157]
  In this work, we generalize the QPP task to determine which ranking models are most effective for a given query.<n>Our results show that predicting the best ranker for a query is considerably more difficult than predicting the relative difficulty of queries for a given ranker.
  arXiv  Detail & Related papers  (2026-01-24T08:10:37Z)
• Predicting Retrieval Utility and Answer Quality in Retrieval-Augmented Generation [24.439170886636788]
  Key challenge for improving RAG is to predict both the utility of retrieved documents and the quality of the final answers in terms of correctness and relevance.<n>We define two prediction tasks within RAG: retrieval performance prediction and generation performance prediction.<n>We argue that reader-centric features, such as the LLM's perplexity of the retrieved context conditioned on the input query, can further enhance prediction accuracy.
  arXiv  Detail & Related papers  (2026-01-20T23:59:54Z)
• Revisiting Query Variants: The Advantage of Retrieval Over Generation of Query Variants for Effective QPP [24.439170886636788]
  We propose a method that retrieves QVs from a training set for a given target query of QPP.<n>To achieve a high recall in retrieving queries with the most similar information needs, we extend the directly retrieved QVs by a second retrieval.<n>Our experiments, conducted on TREC DL'19 and DL'20, show that the QPP methods with QVs retrieved by our method outperform the best-performing existing generated-QV-based QPP approaches by as much as around 20%.
  arXiv  Detail & Related papers  (2025-10-02T19:36:58Z)
• Query Performance Prediction using Relevance Judgments Generated by Large Language Models [53.97064615557883]
  We propose a new Query performance prediction (QPP) framework using automatically generated relevance judgments (QPP-GenRE)<n>QPP-GenRE decomposes QPP into independent subtasks of predicting relevance of each item in a ranked list to a given query.<n>We predict an item's relevance by using open-source large language models (LLMs) to ensure scientific relevance.
  arXiv  Detail & Related papers  (2024-04-01T09:33:05Z)
• Query Performance Prediction: From Ad-hoc to Conversational Search [55.37199498369387]
  Query performance prediction (QPP) is a core task in information retrieval. Research has shown the effectiveness and usefulness of QPP for ad-hoc search. Despite its potential, QPP for conversational search has been little studied.
  arXiv  Detail & Related papers  (2023-05-18T12:37:01Z)
• Toward Unsupervised Realistic Visual Question Answering [70.67698100148414]
  We study the problem of realistic VQA (RVQA), where a model has to reject unanswerable questions (UQs) and answer answerable ones (AQs) We first point out 2 drawbacks in current RVQA research, where (1) datasets contain too many unchallenging UQs and (2) a large number of annotated UQs are required for training. We propose a new testing dataset, RGQA, which combines AQs from an existing VQA dataset with around 29K human-annotated UQs. This combines pseudo UQs obtained by randomly pairing images and questions, with an
  arXiv  Detail & Related papers  (2023-03-09T06:58:29Z)
• Harvesting and Refining Question-Answer Pairs for Unsupervised QA [95.9105154311491]
  We introduce two approaches to improve unsupervised Question Answering (QA) First, we harvest lexically and syntactically divergent questions from Wikipedia to automatically construct a corpus of question-answer pairs (named as RefQA) Second, we take advantage of the QA model to extract more appropriate answers, which iteratively refines data over RefQA.
  arXiv  Detail & Related papers  (2020-05-06T15:56:06Z)
• Template-Based Question Generation from Retrieved Sentences for Improved Unsupervised Question Answering [98.48363619128108]
  We propose an unsupervised approach to training QA models with generated pseudo-training data. We show that generating questions for QA training by applying a simple template on a related, retrieved sentence rather than the original context sentence improves downstream QA performance.
  arXiv  Detail & Related papers  (2020-04-24T17:57:45Z)

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.