Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerability
sigir26-227 · Full research paper · Jia-Huei Ju, Eugene Yang, Trevor V. Adriaanse, Suzan Verberne, Andrew Yates
Multi-Hop and Iterative Retrieval Re · 25% Evidence Selection and Context Refin · 25% Evaluation Metrics and User Models · 25% Dense Bi-Encoder Training and Repres · 25%
Abstract
Long-form Retrieval-Augmented Generation (RAG) brings the challenge of coverage-based ranking, because ranking methods must ensure the inclusion of comprehensive relevant nuggets (i.e., facts), which can thereby be synthesized into a comprehensive output. In this work, we propose CoveR, a dense retrieval method optimized for coverage-aware retrieval scenarios. CoveR is a bi-encoder trained with the coverage-based contrastive and distillation objectives, which enables CoveR to capture diverse aspects of information needs. To train CoveR, we create the SCOPE dataset, which comprises 90K training pairs from Researchy Questions with synthetic coverage signals augmented from sub-question answerability judgments generated by LLMs. Our empirical experiments show that CoveR enhances nugget coverage by 10% over strong dense retrieval baselines without sacrificing its relevance-based retrieval capability. Further ablation studies validate the importance of our proposed learning method, showing that CoveR achieves a superior trade-off between relevance- and coverage-based ranking, which is essential for long-form RAG.
Assigned reviewers
| # | Reviewer | Match | Why (closest evidence publications in the taxonomy) | |
|---|---|---|---|---|
| 1 | Keping Bi | 53 | 71 Beyond Relevance: Utility-Centric Retrieval in the LLM Era (2026) Evidence Selection and Context Refinement 57 Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation (2025) Evidence Selection and Context Refinement 49 L2R: Lifelong Learning for First-stage Retrieval with Backward-Compatible Representations (2023) Efficient Retrieval and Indexing Systems › Others |
|
| 2 | Daiting Shi | 52 | 57 Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation (2025) Evidence Selection and Context Refinement 50 Pre-trained Language Model-based Retrieval and Ranking for Web Search (2023) Learned Sparse Retrieval Efficiency 48 MA4DIV: Multi-Agent Reinforcement Learning for Search Result Diversification (2025) Evaluation Metrics and User Models |
|
| 3 | Venktesh V | 50 | 61 The Surprising Effectiveness of Rankers trained on Expanded Queries (2024) Evidence Selection and Context Refinement 55 Reproducing Adaptive Reranking for Reasoning-Intensive IR (2026) Evidence Selection and Context Refinement 54 SUNAR: Semantic Uncertainty based Neighborhood Aware Retrieval for Complex QA (2025) Multi-Hop and Iterative Retrieval Reasoning |
Area chair
| Area chair | Match | |
|---|---|---|
| Fernando Diaz 0001 | 55 |
Area-chair candidates (7)
| Fernando Diaz 0001 assigned | 55 | 12 papers | |
| Hongjin Qian | 54 | 12 papers | |
| Xiaoxi Li 0005 | 51 | 15 papers | |
| Zhijing Wu 0001 | 50 | 9 papers | |
| Jun Xu 0001 | 47 | 2 papers | |
| Xiaoxue Zang | 45 | 4 papers | |
| Chenyan Xiong | 45 | 15 papers |
Candidates from the panel ranked by match score
| # | Reviewer | Match | Load | Why | |
|---|---|---|---|---|---|
| 1 | Jing Liu 0022 | 56 | 3 | 52 RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking (2021) Dense Bi-Encoder Training and Representation Learning 51 Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation (2026) Evidence Selection and Context Refinement |
|
| 3 | Tetsuya Sakai | 55 | 3 | 51 ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval (2024) Conversational Search and Retrieval 48 Summary of the NTCIR-10 INTENT-2 task: subtopic mining and search result diversification (2013) Evaluation Metrics and User Models |
|
| 4 | Xinyu Ma 0001 COI: co-author | 54 | 3 | 50 Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models (2026) Evidence Selection and Context Refinement 47 B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval (2021) Sparse and Dense Retrieval Encoders |
|
| 6 | Keping Bi assigned | 53 | 3 | 71 Beyond Relevance: Utility-Centric Retrieval in the LLM Era (2026) Evidence Selection and Context Refinement 57 Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation (2025) Evidence Selection and Context Refinement |
|
| 7 | Ruqing Zhang 0001 COI: co-author | 53 | 3 | 58 Boosting Retrieval-Augmented Generation with Generation-Augmented Retrieval: A Co-Training Approach (2025) Generative Retrieval 50 Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning (2026) Multi-Hop and Iterative Retrieval Reasoning |
|
| 8 | Daiting Shi assigned | 52 | 3 | 57 Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation (2025) Evidence Selection and Context Refinement 50 Pre-trained Language Model-based Retrieval and Ranking for Web Search (2023) Learned Sparse Retrieval Efficiency |
|
| 9 | Mark D. Smucker | 52 | 3 | 48 Offline Evaluation by Maximum Similarity to an Ideal Ranking (2020) Evaluation Metrics and User Models 48 Assessing Top- Preferences (2021) Evaluation Metrics and User Models |
|
| 12 | Venktesh V assigned | 50 | 3 | 61 The Surprising Effectiveness of Rankers trained on Expanded Queries (2024) Evidence Selection and Context Refinement 55 Reproducing Adaptive Reranking for Reasoning-Intensive IR (2026) Evidence Selection and Context Refinement |
|
| 13 | Negar Arabzadeh | 49 | 3 | 60 Can QPP Choose the Right Query variant? Evaluating Query Variant Selection for RAG Pipelines (2026) Evidence Selection and Context Refinement 49 Predicting Efficiency/Effectiveness Trade-offs for Dense vs. Sparse Retrieval Strategy Selection (2021) Efficient Retrieval and Indexing |
|
| 14 | Chen Zhao 0013 | 49 | 3 | 65 SportReason: Evaluating Retrieval-Augmented Reasoning across Tables and Text for Sports Question Answering (2025) Multi-Hop and Iterative Retrieval Reasoning 60 Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems (2026) Reasoning-Intensive Retrieval and Ranking |
|
| 15 | Shengyao Zhuang | 48 | 3 | 56 To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers (2022) Query Reformulation and Expansion 49 PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval (2024) Text Embedding and Representation Learning |
|
| 16 | Shuaiqiang Wang COI: co-author | 48 | 3 | 50 Enhancing Retrieval-Augmented Generation via Evidence Tree Search (2025) Evidence Selection and Context Refinement 50 Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning (2025) Multi-Hop and Iterative Retrieval Reasoning |
|
| 17 | Xiao Wang 0043 | 48 | 3 | 47 An Inspection of the Reproducibility and Replicability of TCT-ColBERT (2022) Learned Sparse Retrieval Efficiency 47 Unsupervised Dense Retrieval with Conterfactual Contrastive Learning (2026) Robustness and Adversarial IR |
|
| 18 | Sheng-Chieh Lin COI: co-author | 47 | 3 | 51 Contextualized Query Embeddings for Conversational Search (2021) Conversational Search and Retrieval 47 Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval (2023) Dense Bi-Encoder Training and Representation Learning |
|
| 19 | Xueguang Ma | 47 | 3 | 56 To Interpolate or not to Interpolate: PRF, Dense and Sparse Retrievers (2022) Query Reformulation and Expansion 54 Toward Best Practices for Training Multilingual Dense Retrieval Models (2024) Evaluation Resources and Tools |
|
| 20 | Navve Wasserman | 47 | 3 | 53 DocReRank: Single-Page Hard Negative Query Generation for Training Multi-Modal RAG Rerankers (2025) Universal Multimodal Embedding and MLLM Retrieval 53 REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark (2025) Universal Multimodal Embedding and MLLM Retrieval |
|
| 21 | Jingtao Zhan | 47 | 3 | 49 Dynamic and Parametric Retrieval-Augmented Generation (2025) Multi-Hop and Iterative Retrieval Reasoning 48 Optimizing Dense Retrieval Model Training with Hard Negatives (2021) Dense Bi-Encoder Training and Representation Learning |
|
| 22 | Weiwei Sun 0001 | 47 | 3 | 50 Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models (2026) Evidence Selection and Context Refinement 45 Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents (2023) Reasoning-Intensive Retrieval and Ranking |
|
| 24 | Yuchen Li 0006 | 46 | 3 | 51 Retain to Refine: Adaptive Online Question Answering via Query Routing and Long-Short Memory (2026) Agentic and Deep Search RAG 50 Enhancing Retrieval-Augmented Generation via Evidence Tree Search (2025) Evidence Selection and Context Refinement |
|
| 25 | Corby Rosset | 46 | 3 | 53 Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention (2020) Multi-Hop and Iterative Retrieval Reasoning 47 Generic Intent Representation in Web Search (2019) Text Embedding and Representation Learning |
|
| 26 | Yujia Zhou 0002 | 46 | 3 | 58 CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks (2024) Generative Retrieval 58 Grounding Language Model with Chunking-Free In-Context Retrieval (2024) Generative Retrieval |
|
| 27 | Tingyu Song | 45 | 3 | 58 LimRank: Less is More for Reasoning-Intensive Information Reranking (2025) Evidence Selection and Context Refinement 51 Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems (2026) Reasoning-Intensive Retrieval and Ranking |
|
| 28 | Jinheon Baek | 45 | 3 | 54 Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity (2024) Multi-Hop and Iterative Retrieval Reasoning 51 Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks (2023) Retrieval-Augmented and Open-Domain QA |
|
| 30 | Andrew Parry COI: co-author | 45 | 3 | 59 Constructing and Evaluating Declarative RAG Pipelines in PyTerrier (2025) Retrieval Toolkits and Reproducibility 43 Optimal Re-Ranking Depth (2026) Query Performance Prediction |
|
| 32 | Leif Azzopardi COI: co-author | 45 | 3 | 53 Conversational Gold: Evaluating Personalized Conversational Search System Using Gold Nuggets (2025) Interactive Information Seeking and Evaluation 46 Measuring Bias in a Ranked List Using Term-Based Representations (2024) Evaluation Metrics and User Models |
|
| 33 | Jurek Leonhardt | 44 | 3 | 51 Efficient Neural Ranking using Forward Indexes (2022) Learned Sparse Retrieval Efficiency 51 Efficient Neural Ranking Using Forward Indexes and Lightweight Encoders (2024) Learned Sparse Retrieval Efficiency |
|
| 34 | Xingyu Tan 0001 | 44 | 3 | 48 HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning (2025) KG-Augmented LLM Reasoning 48 Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning (2025) KG-Augmented LLM Reasoning |
|
| 35 | Shu Zhou 0002 | 44 | 3 | 55 SCORE-RAG: Self-Correcting Exploration-Exploitation Retrieval for Multi-hop Question Answering (2026) Multi-Hop and Iterative Retrieval Reasoning 49 DynKGRAG: A framework for dynamic knowledge graph construction and multi-hop querying over numerical and textual data (2026) Multi-Hop and Iterative Retrieval Reasoning |
|
| 36 | Adam Jatowt | 43 | 3 | 53 TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions (2026) Domain-Specific and Structured Retrieval 44 BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination (2026) Reasoning-Intensive Retrieval and Ranking |
|
| 37 | Armin Toroghi | 42 | 3 | 48 Self-supervised Contrastive BERT Fine-tuning for Fusion-Based Reviewed-Item Retrieval (2023) Dense Bi-Encoder Training and Representation Learning 35 Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitation (2024) Conversational Recommendation Systems |