mlsanityData to 7 Oct 2026

LANCER: LLM Reranking for Nugget Coverage

arXiv 2601.22008 ↗First posted 29 Jan 2026cs.IRcited by 2

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Unlike short-form retrieval-augmented generation (RAG), such as factoid question answering, long-form RAG requires retrieval to provide documents covering a wide range of relevant information. Automated report generation exemplifies this setting: it requires not only relevant information but also a more elaborate response with comprehensive information. Yet, existing retrieval methods are primarily optimized for relevance ranking rather than information coverage. To address this limitation, we propose LANCER, an LLM-based reranking method for nugget coverage. LANCER predicts what sub-questions should be answered to satisfy an information need, predicts which documents answer these sub-questions, and reranks documents in order to provide a ranked list covering as many information nuggets as possible. Our empirical results show that LANCER enhances the quality of retrieval as measured by nugget coverage metrics, achieving higher α-nDCG and information coverage than other LLM-based reranking methods. Our oracle analysis further reveals that sub-question generation plays an essential role.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 41 of its 54 references that are in the map. First posted on arXiv 29 Jan 2026.

Builds on

41 of 54 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023REPLUG: Retrieval-Augmented Black-Box Language Models30 Jan
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May
  3. 2020REALM: Retrieval-Augmented Language Model Pre-Training10 Feb

Other references · 38

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  3. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  4. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  5. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  6. 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
  7. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  8. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 373
  9. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 356
  10. 2023Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflictscited by 333
  11. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 302
  12. 2018Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategiescited by 292
26 more
  1. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 231
  2. 2019Multi-Stage Document Ranking with BERTcited by 200
  3. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 164
  4. 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 151
  5. 2022RankT5: Fine-Tuning T5 for Text Ranking with Ranking Lossescited by 114
  6. 2023Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labelscited by 86
  7. 2023Zero-Shot Listwise Document Reranking with a Large Language Modelcited by 81
  8. 2024SPLADE-v3: New baselines for SPLADEcited by 69
  9. 2024FIRST: Faster Improved Listwise Reranking with Single Token Decodingcited by 54
  10. 2023A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Modelscited by 53
  11. 2024Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer Frameworkcited by 28
  12. 2024DMQR-RAG: Diverse Multi-Query Rewriting for RAGcited by 26
  13. 2024On the Evaluation of Machine-Generated Reportscited by 23
  14. 2024From Single to Multi: How LLMs Hallucinate in Multi-Document Summarizationcited by 17
  15. 2025GINGER: Grounded Information Nugget-Based Generation of Responsescited by 16
  16. 2025Auto-ARGUE: LLM-Based Report Generation Evaluationcited by 14
  17. 2025Overview of the TREC 2024 NeuCLIR Trackcited by 13
  18. 2024Open-World Evaluation for Retrieving Diverse Perspectivescited by 11
  19. 2025LLMs can be Fooled into Labelling a Document as Relevant (best caf'e near me; this paper is perfectly relevant)cited by 10
  20. 2024A Workbench for Autograding Retrieve/Generate Systemscited by 9
  21. 2025Controlled Retrieval-augmented Context Evaluation for Long-form RAGcited by 9
  22. 2025Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connectorcited by 9
  23. 2025HLTCOE at LiveRAG: GPT-Researcher using ColBERT retrievalcited by 6
  24. 2021IntenT5: Search Result Diversification using Causal Language Modelscited by 4
  25. 2025Reason to Retrieve: Enhancing Query Understanding through Decomposition and Interpretationcited by 4
  26. 2024Vector Retrieval with Similarity and Diversity: How Hard Is It?cited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Search for Coverage: Learning Coverage-Aware Retrieval with Augmented Sub-Question Answerabilitycited by 0
  2. 2026Re:CAP - Auditing Retrieval Coverage in Production RAG Pipelinescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion
  2. 2026Beyond the Reranker: Do RAG Retrieval Enhancements Help Once a Strong Reranker Is Present?
  3. 2026Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making Problem
  4. 2025Question Decomposition for Retrieval-Augmented Generation
  5. 2025InfoGain-RAG: Boosting Retrieval-Augmented Generation via Document Information Gain-based Reranking and Filtering
  6. 2026Better Together: Complementary Query Rewriting Under a Strong RAG Baseline
  7. 2026SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG
  8. 2025RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets