mlsanityData to 14 Oct 2026

Inter-Passage Verification for Multi-evidence Multi-answer QA

arXiv 2506.00425 ↗First posted 31 May 2025cs.CLcited by 1

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Multi-answer question answering (QA), where questions can have many valid answers, presents a significant challenge for existing retrieval-augmented generation-based QA systems, as these systems struggle to retrieve and then synthesize a large number of evidence passages. To tackle these challenges, we propose a new multi-answer QA framework -- Retrieval-augmented Independent Reading with Inter-passage Verification (RI2VER). Our framework retrieves a large set of passages and processes each passage individually to generate an initial high-recall but noisy answer set. Then we propose a new inter-passage verification pipeline that validates every candidate answer through (1) Verification Question Generation, (2) Gathering Additional Evidence, and (3) Verification with inter-passage synthesis. Evaluations on the QAMPARI and RoMQA datasets demonstrate that our framework significantly outperforms existing baselines across various model sizes, achieving an average F1 score improvement of 11.17%. Further analysis validates that our inter-passage verification pipeline enables our framework to be particularly beneficial for questions requiring multi-evidence synthesis.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 48 of its 64 references that are in the map. First posted on arXiv 31 May 2025.

Builds on

48 of 64 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answering4 Sep
  2. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents16 Apr
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 45

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  7. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  8. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  9. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  10. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  11. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
33 more
  1. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  2. 2023Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizescited by 737
  3. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  4. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  5. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
  6. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 472
  7. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  8. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 433
  9. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 390
  10. 2024Measuring short-form factuality in large language modelscited by 373
  11. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  12. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  13. 2022ASQA: Factoid Questions Meet Long-Form Answerscited by 234
  14. 2023Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?cited by 168
  15. 2024Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QAcited by 122
  16. 2024VERISCORE: Evaluating the factuality of verifiable claims in long-form text generationcited by 117
  17. 2024Jasper and Stella: distillation of SOTA embedding modelscited by 112
  18. 2018The Fact Extraction and VERification (FEVER) Shared Taskcited by 108
  19. 2023Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Methodcited by 97
  20. 2023LLatrieval: LLM-Verified Retrieval for Verifiable Generationcited by 52
  21. 2023Effective Large Language Model Adaptation for Improved Grounding and Citation Generationcited by 45
  22. 2021Joint Passage Ranking for Diverse Multi-Answer Retrievalcited by 43
  23. 2022QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphscited by 42
  24. 2023Language Models Hallucinate, but May Excel at Fact Verificationcited by 37
  25. 2024DMQR-RAG: Diverse Multi-Query Rewriting for RAGcited by 27
  26. 2024AmbigDocs: Reasoning across Documents on Different Entities under the Same Namecited by 21
  27. 2020Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Predictioncited by 19
  28. 2022RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answeringcited by 19
  29. 2024Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answerscited by 18
  30. 2023Answering Ambiguous Questions via Iterative Promptingcited by 13
  31. 2021Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Frameworkcited by 11
  32. 2021Design Challenges for a Multi-Perspective Search Enginecited by 7
  33. 2023Answering Ambiguous Questions with a Database of Questions, Answers, and Revisionscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026D2-ScaleAgent: Dual-Dimensional Scaling for Long Document Understandingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SURE-RAG: Sufficiency and Uncertainty-Aware Evidence Verification for Selective Retrieval-Augmented Generation
  2. 2026S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA
  3. 2026PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs
  4. 2026QUBO-Optimized Evidence Selection for Retrieval-Augmented Question Answering with Unconventional Solvers
  5. 2025Beyond Independent Passages: Adaptive Passage Combination Retrieval for Retrieval Augmented Open-Domain Question Answering
  6. 2026MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering
  7. 2025Uncertainty Quantification in Retrieval Augmented Question Answering
  8. 2026Dual-Confidence Contrastive Decoding for Retrieval-Augmented Generation