Consensus-Anchored Expansion for Noise-Resilient Re-ranking
sigir26-110 · Full research paper · Nischal Subedi, Cencheng Shen
Query Reformulation and Expansion · 50% Cross-Encoder and Neural Reranking · 50%
Abstract
Dense retrievers bridge vocabulary gaps but suffer from semantic drift, ranking topically similar passages that are not actually relevant to the query. Sparse retrievers like BM25 are generally less prone to such false positives but miss paraphrases. We observe that these failure modes are complementary, with relevant passages concentrated in regions where both retrievers score highly, while single-retriever confidence proves unreliable. Building on this insight, we propose AgreRank, a re-ranking method that leverages sparse-dense consensus for query expansion. AgreRank identifies anchor documents where both retrievers agree, expands the query through these verified anchors, and applies geometric gating to suppress drift from the original intent. On TREC Deep Learning 2021 and 2022, AgreRank improves over Dense+CE by 3.4--5.7% and over RRF+CE by 3.7--5.6% under identical retrieval and reranking components, achieving nDCG@10 of 0.706 and 0.627 with a lightweight 33M-parameter cross-encoder. These gains require no additional parameters or training, demonstrating that more effective use of retrieval signals offers a practical alternative to model scaling.
Assigned reviewers
| # | Reviewer | Match | Why (closest evidence publications in the taxonomy) | |
|---|---|---|---|---|
| 1 | Xiao Wang 0043 | 58 | 69 Effective Contrastive Weighting for Dense Query Expansion (2023) Query Reformulation and Expansion 69 Neural Pseudo-Relevance Feedback Models for Sparse and Dense Retrieval (2022) Query Reformulation and Expansion 69 ColBERT-PRF: Semantic Pseudo-Relevance Feedback for Dense Passage and Document Retrieval (2023) Query Reformulation and Expansion |
|
| 2 | Shengyao Zhuang | 57 | 73 TILDE: Term Independent Likelihood moDEl for Passage Re-ranking (2021) Efficient Retrieval and Indexing 70 To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers (2022) Query Reformulation and Expansion 69 Revisiting Document Expansion and Filtering for Effective First-Stage Retrieval (2024) Query Reformulation and Expansion |
|
| 3 | Jurek Leonhardt | 56 | 68 Extractive Explanations for Interpretable Text Ranking (2023) Cross-Encoder and Neural Reranking 66 Understanding the User: An Intent-Based Ranking Dataset (2024) Query Reformulation and Expansion 48 Data Augmentation for Sample Efficient and Robust Document Ranking (2024) Ranking Distillation and Adaptation |
Area chair
| Area chair | Match | |
|---|---|---|
| Chenyan Xiong | 50 |
Area-chair candidates (7)
| Chenyan Xiong assigned | 50 | 15 papers | |
| Fernando Diaz 0001 | 48 | 12 papers | |
| Zhijing Wu 0001 | 47 | 9 papers | |
| Xiaoxue Zang | 46 | 4 papers | |
| Jun Xu 0001 | 42 | 2 papers | |
| Xiaoyi Zeng | 39 | 11 papers | |
| Hongjin Qian | 39 | 12 papers |
Candidates from the panel ranked by match score
| # | Reviewer | Match | Load | Why | |
|---|---|---|---|---|---|
| 1 | Xiao Wang 0043 assigned | 58 | 3 | 69 Effective Contrastive Weighting for Dense Query Expansion (2023) Query Reformulation and Expansion 69 Neural Pseudo-Relevance Feedback Models for Sparse and Dense Retrieval (2022) Query Reformulation and Expansion |
|
| 2 | Shengyao Zhuang assigned | 57 | 3 | 73 TILDE: Term Independent Likelihood moDEl for Passage Re-ranking (2021) Efficient Retrieval and Indexing 70 To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers (2022) Query Reformulation and Expansion |
|
| 3 | Jurek Leonhardt assigned | 56 | 3 | 68 Extractive Explanations for Interpretable Text Ranking (2023) Cross-Encoder and Neural Reranking 66 Understanding the User: An Intent-Based Ranking Dataset (2024) Query Reformulation and Expansion |
|
| 4 | Negar Arabzadeh | 53 | 3 | 68 Enhanced Retrieval Effectiveness through Selective Query Generation (2024) Query Reformulation and Expansion 68 ReFormeR: Learning and Applying Explicit Query Reformulation Patterns (2026) Query Reformulation and Expansion |
|
| 6 | Xueguang Ma | 48 | 3 | 73 To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers (2022) Query Reformulation and Expansion 68 Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study (2022) Query Reformulation and Expansion |
|
| 8 | Falk Scholer | 48 | 3 | 69 Ranking Documents by Answer-Passage Quality (2018) Retrieval-Augmented and Open-Domain QA 69 Document Summarization for Answering Non-Factoid Queries (2018) Retrieval-Augmented and Open-Domain QA |
|
| 9 | Jingtao Zhan | 48 | 3 | 70 An Analysis of BERT in Document Ranking (2020) Sparse and Dense Retrieval Encoders 68 Leveraging Passage-level Cumulative Gain for Document Ranking (2020) Cross-Encoder and Neural Reranking |
|
| 12 | Daiting Shi | 46 | 3 | 68 Population-Guided Intent-Aware Query Rewriting for Web Search (2026) Query Reformulation and Expansion 64 Accurate and Efficient Personalized Query Rewriting in Baidu Search (2026) Query Reformulation and Expansion |
|
| 13 | Antonio Mallia | 46 | 3 | 68 Unveiling DIME: Reproducibility, Generalizability, and Formal Analysis of Dimension Importance Estimation for Dense Retrieval (2025) Query Reformulation and Expansion 56 E2Rank: Efficient and Effective Layer-Wise Reranking (2025) Learned Sparse Retrieval Efficiency |
|
| 14 | Yuchen Li 0006 | 45 | 3 | 52 ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability (2026) LLM-Based Reranking 49 S2phere: Semi-Supervised Pre-training for Web Search over Heterogeneous Learning to Rank Data (2023) Web-Scale Learning to Rank |
|
| 15 | Rolf Jagerman | 45 | 3 | 100 Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers? (2024) Query Reformulation and Expansion 67 RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses (2023) Cross-Encoder and Neural Reranking |
|
| 16 | Zhen Qin 0001 | 44 | 3 | 100 Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers? (2024) Query Reformulation and Expansion 52 Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing (2024) LLM-Based Reranking |
|
| 17 | Xuanhui Wang | 44 | 3 | 100 Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers? (2024) Query Reformulation and Expansion 70 Accurate language model estimation with document expansion (2005) Query Reformulation and Expansion |
|
| 18 | Idan Szpektor | 44 | 3 | 68 Improving recommendation for long-tail queries via templates (2011) Query Reformulation and Expansion 68 From query to question in one click: suggesting synthetic questions to searchers (2013) Query Reformulation and Expansion |
|
| 19 | Franco Maria Nardini | 44 | 3 | 57 Expansion via Prediction of Importance with Contextualization (2020) Sparse and Dense Retrieval Encoders 56 Efficient Re-ranking with Cross-encoders via Early Exit (2025) Learned Sparse Retrieval Efficiency |
|
| 20 | Andrew Parry | 43 | 3 | 77 Optimal Re-Ranking Depth (2026) Query Performance Prediction 45 "In-Context Learning" or: How I learned to stop worrying and love "Applied Information Retrieval" (2024) Sparse and Dense Retrieval Encoders |
|
| 21 | Venktesh V | 43 | 3 | 67 Reproducing Adaptive Reranking for Reasoning-Intensive IR (2026) Evidence Selection and Context Refinement 66 Understanding the User: An Intent-Based Ranking Dataset (2024) Query Reformulation and Expansion |
|
| 22 | Ruqing Zhang 0001 | 43 | 3 | 43 B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval (2021) Sparse and Dense Retrieval Encoders 43 PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval (2021) Sparse and Dense Retrieval Encoders |
|
| 23 | Sheng-Chieh Lin | 43 | 3 | 57 Improving Conversational Passage Re-ranking with View Ensemble (2023) Conversational Search and Retrieval 54 Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting (2021) Conversational Search and Retrieval |
|
| 24 | Xinyu Ma 0001 | 43 | 3 | 52 Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents (2023) Reasoning-Intensive Retrieval and Ranking 50 ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability (2026) LLM-Based Reranking |
|
| 25 | Shuaiqiang Wang | 42 | 3 | 48 GS2P: a generative pre-trained learning to rank model with over-parameterization for web-scale search (2024) Web-Scale Learning to Rank 48 GS2P: A Generative Pre-trained Learning to Rank Model with Over-parameterization for Web-Scale Search (Extended Abstract) (2024) Web-Scale Learning to Rank |
|
| 27 | Gustavo Penha | 42 | 3 | 68 Improving Content Retrievability in Search with Controllable Query Generation (2023) Query Reformulation and Expansion 67 Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators (2022) Query Reformulation and Expansion |
|
| 28 | Tetsuya Sakai | 42 | 3 | 68 Flexible Pseudo-Relevance Feedback Using Optimization Tables (2001) Query Reformulation and Expansion 42 ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval (2024) Conversational Search and Retrieval |
|
| 29 | Weiwei Sun 0001 | 41 | 3 | 54 TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy (2025) Reasoning-Intensive Retrieval and Ranking 52 Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents (2023) Reasoning-Intensive Retrieval and Ranking |
|
| 30 | Jialong Wu 0007 | 41 | 3 | 68 AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptation (2025) Query Reformulation and Expansion 68 AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment (2025) Query Reformulation and Expansion |
|
| 31 | Sebastian Bruch 0001 | 41 | 3 | 48 Training Efficient Tree-Based Models for Document Ranking (2013) Web-Scale Learning to Rank 46 TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank (2019) Retrieval Toolkits and Reproducibility |
|
| 32 | Keping Bi | 40 | 3 | 48 Extracting search-focused key n-grams for relevance ranking in web search (2012) Web-Scale Learning to Rank 44 Reproducibility Analysis and Enhancements for Multi-aspect Dense Retriever with Aspect Learning (2024) Retrieval Toolkits and Reproducibility |
|
| 33 | Jinheon Baek | 40 | 3 | 68 Database-Augmented Query Representation for Information Retrieval (2025) Query Reformulation and Expansion 41 Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement (2023) Conversational Search and Retrieval |
|
| 34 | Corby Rosset | 39 | 3 | 57 Contextual Re-Ranking with Behavior Aware Transformers (2020) Conversational Search and Retrieval 42 Optimizing Query Evaluations Using Reinforcement Learning for Web Search (2018) Efficient Retrieval and Indexing |
|
| 36 | Adam Jatowt | 39 | 3 | 68 Search Intent Discovery by Structurization of Community QA Contents (2012) Query Reformulation and Expansion 54 BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination (2026) Reasoning-Intensive Retrieval and Ranking |