mlsanityData to 7 Oct 2026

Analysis of Plan-based Retrieval for Grounded Text Generation

arXiv 2408.10490 ↗First posted 20 Aug 2024cs.CL cs.IRcited by 5

Not on the map. Why?

Abstract (arXiv)

In text generation, hallucinations refer to the generation of seemingly coherent text that contradicts established knowledge. One compelling hypothesis is that hallucinations occur when a language model is given a generation task outside its parametric knowledge (due to rarity, recency, domain, etc.). A common strategy to address this limitation is to infuse the language models with retrieval mechanisms, providing the model with relevant knowledge for the task. In this paper, we leverage the planning capabilities of instruction-tuned LLMs and analyze how planning can be used to guide retrieval to further reduce the frequency of hallucinations. We empirically evaluate several variations of our proposed approach on long-form text generation tasks. By improving the coverage of relevant facts, plan-guided retrieval and generation can produce more informative responses while providing a higher rate of attribution to source documents.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 50 of its 67 references that are in the map. First posted on arXiv 20 Aug 2024.

Builds on

50 of 67 references.

References · 50

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  5. 2019Language Models as Knowledge Bases?cited by 1,922
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  7. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,259
  8. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  9. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  10. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  11. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  12. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
38 more
  1. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  2. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  3. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  4. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  5. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 349
  6. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 308
  7. 2023Evaluating Verifiability in Generative Search Enginescited by 297
  8. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 286
  9. 2021Measuring Attribution in Natural Language Generation Modelscited by 253
  10. 2017Challenges in Data-to-Document Generationcited by 226
  11. 2020Modifying Memories in Transformer Modelscited by 222
  12. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 200
  13. 2020How Context Affects Language Models' Factual Predictionscited by 181
  14. 2022Large Language Models with Controllable Working Memorycited by 169
  15. 2021NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristicscited by 153
  16. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 150
  17. 2020NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraintscited by 146
  18. 2017Faithful to the Original: Fact Aware Neural Abstractive Summarizationcited by 141
  19. 2021Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answeringcited by 131
  20. 2023The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediationscited by 130
  21. 2021Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarizationcited by 128
  22. 2020Evaluating Factuality in Generation with Dependency-level Entailmentcited by 122
  23. 2022DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answeringcited by 93
  24. 2023Controlled Text Generation with Natural Language Instructionscited by 87
  25. 2023TrueTeacher: Learning Factual Consistency Evaluation with Large Language Modelscited by 82
  26. 2023Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedbackcited by 71
  27. 2023SILO Language Models: Isolating Legal Risk In a Nonparametric Datastorecited by 71
  28. 2023PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptionscited by 53
  29. 2022Conditional Generation with a Question-Answering Blueprintcited by 44
  30. 2023DelucionQA: Detecting Hallucinations in Domain-specific Question Answeringcited by 43
  31. 2023Diving Deep into Modes of Fact Hallucinations in Dialogue Systemscited by 32
  32. 2023Faithfulness-Aware Decoding Strategies for Abstractive Summarizationcited by 31
  33. 2021WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipediacited by 23
  34. 2023Text-Blueprint: An Interactive Platform for Plan-based Conditional Generationcited by 9
  35. 2023μPLAN: Summarizing using a Content Plan as Cross-Lingual Bridgecited by 7
  36. 2023Calibrating Likelihoods towards Consistency in Summarization Modelscited by 4
  37. 2023Long-form Question Answering: An Iterative Planning-Retrieval-Generation Approachcited by 4
  38. 2021May the Force Be with Your Copy Mechanism: Enhanced Supervised-Copy Method for Natural Language Generationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

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

5 papers.

  1. 2025Characterizing Deep Research: A Benchmark and Formal Definitioncited by 29
  2. 2025Code Researcher: Deep Research Agent for Large Systems Code and Commit Historycited by 19
  3. 2025TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classificationcited by 4
  4. 2026Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAGcited by 3
  5. 2025Exploration of Plan-Guided Summarization for Narrative Texts: the Case of Small Language Modelscited by 1