mlsanityData to 7 Oct 2026

Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answering

arXiv 2409.02361 ↗First posted 4 Sep 2024cs.CLcited by 10

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

Abstract (arXiv)

The retrieval augmented generation (RAG) framework addresses an ambiguity in user queries in QA systems by retrieving passages that cover all plausible interpretations and generating comprehensive responses based on the passages. However, our preliminary studies reveal that a single retrieval process often suffers from low quality results, as the retrieved passages frequently fail to capture all plausible interpretations. Although the iterative RAG approach has been proposed to address this problem, it comes at the cost of significantly reduced efficiency. To address these issues, we propose the diversify-verify-adapt (DIVA) framework. DIVA first diversifies the retrieved passages to encompass diverse interpretations. Subsequently, DIVA verifies the quality of the passages and adapts the most suitable approach tailored to their quality. This approach improves the QA systems accuracy and robustness by handling low quality retrieval issue in ambiguous questions, while enhancing efficiency.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 27 of its 33 references that are in the map. First posted on arXiv 4 Sep 2024.

Builds on

27 of 33 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2024The Llama 3 Herd of Modelscited by 14,192
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  8. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  9. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  10. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  11. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
13 more
  1. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  2. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  3. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  4. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  5. 2021SituatedQA: Incorporating Extra-Linguistic Contexts into QAcited by 145
  6. 2023Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Frameworkcited by 139
  7. 2019Multi-hop Reading Comprehension through Question Decomposition and Rescoringcited by 119
  8. 2023LLatrieval: LLM-Verified Retrieval for Verifiable Generationcited by 52
  9. 2021Joint Passage Ranking for Diverse Multi-Answer Retrievalcited by 43
  10. 2023Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applicationscited by 28
  11. 2020Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Predictioncited by 19
  12. 2022Query Refinement Prompts for Closed-Book Long-Form Question Answeringcited by 12
  13. 2021Answering Open-Domain Multi-Answer Questions via a Recall-then-Verify Frameworkcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 4.

10 papers.

  1. 2025Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Surveycited by 6
  2. 2025Learning Steerable Clarification Policies with Collaborative Self-playcited by 5
  3. 2026Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrievalcited by 5
  4. 2025Agentic Verification for Ambiguous Query Disambiguationcited by 2
  5. 2025Inter-Passage Verification for Multi-evidence Multi-answer QAcited by 1
  6. 2025MARCH: Evaluating the Intersection of Ambiguity Interpretation and Multi-hop Inferencecited by 1
  7. 2024Isometry pursuitcited by 0
  8. 2026Is a Picture Worth a Thousand Words? Adaptive Multimodal Fact-Checking with Visual Evidence Necessitycited by 0
  9. 2026Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistantscited by 0
  10. 2026Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrievalcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation
  2. 2024RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering
  3. 2026Interpretable Uncertainty for Adaptive Retrieval and Reasoning in Question Answering
  4. 2026Diversity is Not Ambiguity: Toward Accurate and Efficient Ambiguity Detection for Open-Domain QA
  5. 2026AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering
  6. 2025Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home
  7. 2024Semantic Tokens in Retrieval Augmented Generation
  8. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level