mlsanityData to 14 Oct 2026

Plan-and-Refine: Diverse and Comprehensive Retrieval-Augmented Generation

arXiv 2504.07794 ↗First posted 10 Apr 2025cs.CL cs.IRcited by 0

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

Abstract (arXiv)

This paper studies the limitations of (retrieval-augmented) large language models (LLMs) in generating diverse and comprehensive responses, and introduces the Plan-and-Refine (P&R) framework based on a two phase system design. In the global exploration phase, P&R generates a diverse set of plans for the given input, where each plan consists of a list of diverse query aspects with corresponding additional descriptions. This phase is followed by a local exploitation phase that generates a response proposal for the input query conditioned on each plan and iteratively refines the proposal for improving the proposal quality. Finally, a reward model is employed to select the proposal with the highest factuality and coverage. We conduct our experiments based on the ICAT evaluation methodology--a recent approach for answer factuality and comprehensiveness evaluation. Experiments on the two diverse information seeking benchmarks adopted from non-factoid question answering and TREC search result diversification tasks demonstrate that P&R significantly outperforms baselines, achieving up to a 13.1% improvement on the ANTIQUE dataset and a 15.41% improvement on the TREC dataset. Furthermore, a smaller scale user study confirms the substantial efficacy of the P&R framework.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 55 of its 79 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

55 of 79 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct
  2. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering6 Oct

Other references · 53

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  6. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  7. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  8. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  9. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
  10. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  11. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  12. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
38 more
  1. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  2. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  3. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  4. 2024Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inferencecited by 554
  5. 2023TinyStories: How Small Can Language Models Be and Still Speak Coherent English?cited by 449
  6. 2023LaMP: When Large Language Models Meet Personalizationcited by 437
  7. 2024Understanding the planning of LLM agents: A surveycited by 421
  8. 2023Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Modelscited by 349
  9. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Textcited by 220
  10. 2020Evaluating the Evaluation of Diversity in Natural Language Generationcited by 129
  11. 2021KAT: A Knowledge Augmented Transformer for Vision-and-Languagecited by 126
  12. 2023Self-planning Code Generation with Large Language Modelscited by 124
  13. 2024Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoningcited by 110
  14. 2023A Confederacy of Models: a Comprehensive Evaluation of LLMs on Creative Writingcited by 99
  15. 2024Optimization Methods for Personalizing Large Language Models through Retrieval Augmentationcited by 99
  16. 2023Document-Level Machine Translation with Large Language Modelscited by 90
  17. 2024Evaluating Retrieval Quality in Retrieval-Augmented Generationcited by 90
  18. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 83
  19. 2019Long and Diverse Text Generation with Planning-based Hierarchical Variational Modelcited by 62
  20. 2019Jointly Measuring Diversity and Quality in Text Generation Modelscited by 61
  21. 2023Natural Language Reasoning, A Surveycited by 61
  22. 2024Evaluating Gender Bias in Large Language Models via Chain-of-Thought Promptingcited by 50
  23. 2022Retrieval-Enhanced Machine Learningcited by 47
  24. 2025Personalized Generation In Large Model Era: A Surveycited by 45
  25. 2018DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Textcited by 40
  26. 2024Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thoughtcited by 34
  27. 2023LogiCoT: Logical Chain-of-Thought Instruction-Tuningcited by 31
  28. 2024Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximizationcited by 29
  29. 2024Initial Nugget Evaluation Results for the TREC 2024 RAG Track with the AutoNuggetizer Frameworkcited by 28
  30. 2025Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generationcited by 27
  31. 2025ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generationcited by 26
  32. 2019ANTIQUE: A Non-Factoid Question Answering Benchmarkcited by 24
  33. 2024Steering Large Language Models between Code Execution and Textual Reasoningcited by 24
  34. 2024Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Modelscited by 23
  35. 2024Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Modelscited by 21
  36. 2024Embedding And Clustering Your Data Can Improve Contrastive Pretrainingcited by 17
  37. 2024Scaling LLM Inference with Optimized Sample Compute Allocationcited by 16
  38. 2025Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generationcited by 15

50 most cited of 53 All 53 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
  2. 2026DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking
  3. 2024RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation
  4. 2024Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models
  5. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  6. 2026ReFilter: Improving Robustness of Retrieval-Augmented Generation via Gated Filter
  7. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
  8. 2023PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter