When More Reformulations Hurt: Avoiding Drift using Ranker Feedback
sigir26-197 · Full research paper · V Venktesh, Mandeep Rathee, Avishek Anand
Query Reformulation and Expansion · 100%
Abstract
Modern retrieval pipelines increasingly rely on query reformulation and neural reranking to improve effectiveness, but this comes at a significant computational cost and introduces a fundamental tradeoff between recall and query drift. Generating many reformulated queries can substantially increase recall, yet naïvely merging or exhaustively reranking their results is prohibitively expensive. In this work, we argue that the core challenge is not reformulation generation itself, but the adaptive selection of reformulations and their retrieved documents under a strict inference budget.
Assigned reviewers
| # | Reviewer | Match | Why (closest evidence publications in the taxonomy) | |
|---|---|---|---|---|
| 1 | Xiao Wang 0043 | 60 | 77 Improving zero-shot retrieval using dense external expansion (2022) Query Reformulation and Expansion 77 Neural Pseudo-Relevance Feedback Models for Sparse and Dense Retrieval (2022) Query Reformulation and Expansion 77 Effective Contrastive Weighting for Dense Query Expansion (2023) Query Reformulation and Expansion |
|
| 2 | Negar Arabzadeh | 59 | 100 Enhanced Retrieval Effectiveness through Selective Query Generation (2024) Query Reformulation and Expansion 100 ReFormeR: Learning and Applying Explicit Query Reformulation Patterns (2026) Query Reformulation and Expansion 74 A Reproducibility Study of LLM-Based Query Reformulation (2026) Query Reformulation and Expansion |
|
| 3 | Falk Scholer | 51 | 100 Query association for effective retrieval (2002) Query Reformulation and Expansion 70 Can Generative LLMs Create Query Variants for Test Collections? An Exploratory Study (2023) Query Reformulation and Expansion 64 Classifying Term Variants in Query Formulation (2025) User Behavior and Search Interaction |
Area chair
| Area chair | Match | |
|---|---|---|
| Fernando Diaz 0001 | 47 |
Area-chair candidates (6)
| Fernando Diaz 0001 assigned | 47 | 12 papers | |
| Xiaoxue Zang | 47 | 4 papers | |
| Chenyan Xiong | 45 | 15 papers | |
| Jun Xu 0001 | 44 | 2 papers | |
| Zhijing Wu 0001 | 39 | 9 papers | |
| Hongjin Qian | 39 | 12 papers |
Candidates from the panel ranked by match score
| # | Reviewer | Match | Load | Why | |
|---|---|---|---|---|---|
| 1 | Xiao Wang 0043 assigned | 60 | 3 | 77 Improving zero-shot retrieval using dense external expansion (2022) Query Reformulation and Expansion 77 Neural Pseudo-Relevance Feedback Models for Sparse and Dense Retrieval (2022) Query Reformulation and Expansion |
|
| 2 | Negar Arabzadeh assigned | 59 | 3 | 100 Enhanced Retrieval Effectiveness through Selective Query Generation (2024) Query Reformulation and Expansion 100 ReFormeR: Learning and Applying Explicit Query Reformulation Patterns (2026) Query Reformulation and Expansion |
|
| 3 | Falk Scholer assigned | 51 | 3 | 100 Query association for effective retrieval (2002) Query Reformulation and Expansion 70 Can Generative LLMs Create Query Variants for Test Collections? An Exploratory Study (2023) Query Reformulation and Expansion |
|
| 4 | Shengyao Zhuang | 49 | 3 | 77 Revisiting Document Expansion and Filtering for Effective First-Stage Retrieval (2024) Query Reformulation and Expansion 77 Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study (2022) Query Reformulation and Expansion |
|
| 5 | Tetsuya Sakai | 49 | 3 | 100 Flexible Pseudo-Relevance Feedback Using Optimization Tables (2001) Query Reformulation and Expansion 48 Diversification as Risk Minimization (2026) Evaluation Metrics and User Models |
|
| 6 | Xueguang Ma | 48 | 3 | 81 Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study (2022) Query Reformulation and Expansion 70 To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers (2022) Query Reformulation and Expansion |
|
| 9 | Idan Szpektor | 46 | 3 | 100 Improving recommendation for long-tail queries via templates (2011) Query Reformulation and Expansion 100 From query to question in one click: suggesting synthetic questions to searchers (2013) Query Reformulation and Expansion |
|
| 10 | Antonio Mallia | 46 | 3 | 81 Unveiling DIME: Reproducibility, Generalizability, and Formal Analysis of Dimension Importance Estimation for Dense Retrieval (2025) Query Reformulation and Expansion 49 Feature Extraction for Large-Scale Text Collections (2020) Retrieval Toolkits and Reproducibility |
|
| 12 | Jaime Arguello | 44 | 3 | 69 Document Representation and Query Expansion Models for Blog Recommendation (2008) Query Reformulation and Expansion 55 Using Query Performance Predictors to Improve Spoken Queries (2016) Query Performance Prediction |
|
| 14 | Leif Azzopardi | 44 | 3 | 62 Improving sentence retrieval with an importance prior (2010) Query and Document Representation Enhancement 55 Query Variation Performance Prediction for Systematic Reviews (2018) Query Performance Prediction |
|
| 15 | Daiting Shi | 44 | 3 | 100 Population-Guided Intent-Aware Query Rewriting for Web Search (2026) Query Reformulation and Expansion 75 Accurate and Efficient Personalized Query Rewriting in Baidu Search (2026) Query Reformulation and Expansion |
|
| 16 | Gustavo Penha | 44 | 3 | 81 Improving Content Retrievability in Search with Controllable Query Generation (2023) Query Reformulation and Expansion 69 Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators (2022) Query Reformulation and Expansion |
|
| 17 | Jurek Leonhardt COI: co-author | 44 | 3 | 71 Understanding the User: An Intent-Based Ranking Dataset (2024) Query Reformulation and Expansion 45 Data Augmentation for Sample Efficient and Robust Document Ranking (2024) Ranking Distillation and Adaptation |
|
| 18 | Paul Thomas 0001 | 43 | 3 | 70 Can Generative LLMs Create Query Variants for Test Collections? An Exploratory Study (2023) Query Reformulation and Expansion 48 UQV100: A Test Collection with Query Variability (2016) Query Performance Prediction |
|
| 19 | Yuchen Li 0006 | 43 | 3 | 46 GS2P: a generative pre-trained learning to rank model with over-parameterization for web-scale search (2024) Web-Scale Learning to Rank 46 M2oERank: Multi-Objective Mixture-of-Experts Enhanced Ranking for Satisfaction-Oriented Web Search (2025) Web-Scale Learning to Rank |
|
| 20 | Ruqing Zhang 0001 | 42 | 3 | 48 Recent Advances in Generative Information Retrieval (2024) Generative Retrieval 48 Generative Retrieval Meets Multi-Graded Relevance (2024) Generative Retrieval |
|
| 21 | Xuanhui Wang | 42 | 3 | 70 Accurate language model estimation with document expansion (2005) Query Reformulation and Expansion 68 Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers? (2024) Query Reformulation and Expansion |
|
| 22 | Jialong Wu 0007 | 42 | 3 | 73 AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation (2025) Query Reformulation and Expansion 73 AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment (2025) Query Reformulation and Expansion |
|
| 23 | Andrew Parry | 41 | 3 | 49 [inline-graphic not available: see fulltext] SuiteEval: Simplifying Retrieval Benchmarks (2026) Retrieval Toolkits and Reproducibility 45 Optimal Re-Ranking Depth (2026) Query Performance Prediction |
|
| 24 | Franco Maria Nardini | 41 | 3 | 56 Expansion via Prediction of Importance with Contextualization (2020) Sparse and Dense Retrieval Encoders 43 Pairing Clustered Inverted Indexes with κ-NN Graphs for Fast Approximate Retrieval over Learned Sparse Representations (2024) Learned Sparse Retrieval Efficiency |
|
| 25 | Mark D. Smucker | 41 | 3 | 70 Find-similar: similarity browsing as a search tool (2006) Query Reformulation and Expansion 48 Offline Evaluation by Maximum Similarity to an Ideal Ranking (2020) Evaluation Metrics and User Models |
|
| 26 | Sheng-Chieh Lin | 41 | 3 | 60 Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting (2021) Conversational Search and Retrieval 47 Chatty Goose: A Python Framework for Conversational Search (2021) Conversational Search and Retrieval |
|
| 27 | Zhen Qin 0001 | 40 | 3 | 68 Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers? (2024) Query Reformulation and Expansion 48 Transformer Memory as a Differentiable Search Index (2022) Generative Retrieval |
|
| 28 | Jingtao Zhan | 40 | 3 | 64 Query Augmentation with Brain Signals (2024) User Behavior and Search Interaction 43 Combining Multiple Supervision for Robust Zero-Shot Dense Retrieval (2024) Sparse and Dense Retrieval Encoders |
|
| 29 | Xinyu Ma 0001 | 40 | 3 | 48 Model Editing for New Document Integration in Generative Information Retrieval (2026) Generative Retrieval 47 Replication and Exploration of Generative Retrieval over Dynamic Corpora (2025) Generative Retrieval |
|
| 30 | Sara Allawati | 40 | 3 | 64 A Comparative Analysis of Linguistic and Retrieval Diversity in LLM-Generated Search Queries (2025) User Behavior and Search Interaction 42 VulGen: Workshop on Vulnerabilities in Generative Systems for Information Retrieval (2026) Bias Mitigation Methods |
|
| 31 | Shuaiqiang Wang | 40 | 3 | 48 Model Editing for New Document Integration in Generative Information Retrieval (2026) Generative Retrieval 46 GS2P: a generative pre-trained learning to rank model with over-parameterization for web-scale search (2024) Web-Scale Learning to Rank |
|
| 32 | Sebastian Bruch 0001 | 40 | 3 | 47 Effectiveness/efficiency tradeoffs for candidate generation in multi-stage retrieval architectures (2013) Efficient Retrieval and Indexing 46 Training Efficient Tree-Based Models for Document Ranking (2013) Web-Scale Learning to Rank |
|
| 33 | Keping Bi | 40 | 3 | 46 Extracting search-focused key n-grams for relevance ranking in web search (2012) Web-Scale Learning to Rank 46 Reproducibility Analysis and Enhancements for Multi-aspect Dense Retriever with Aspect Learning (2024) Retrieval Toolkits and Reproducibility |
|
| 34 | Rolf Jagerman | 40 | 3 | 68 Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers? (2024) Query Reformulation and Expansion 44 Reliable Confidence Intervals for Information Retrieval Evaluation Using Generative A.I (2024) LLM-Based Relevance Assessment |