mlsanityData to 14 Oct 2026

RARR: Researching and Revising What Language Models Say, Using Language Models

arXiv 2210.08726 ↗First posted 17 Oct 2022cs.CL cs.AI cs.IRcited by 287

Not on the map. Why?

Cited by 38 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Language models (LMs) now excel at many tasks such as few-shot learning, question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their outputs are trustworthy or not, because most LMs do not have any built-in mechanism for attribution to external evidence. To enable attribution while still preserving all the powerful advantages of recent generation models, we propose RARR (Retrofit Attribution using Research and Revision), a system that 1) automatically finds attribution for the output of any text generation model and 2) post-edits the output to fix unsupported content while preserving the original output as much as possible. When applied to the output of several state-of-the-art LMs on a diverse set of generation tasks, we find that RARR significantly improves attribution while otherwise preserving the original input to a much greater degree than previously explored edit models. Furthermore, the implementation of RARR requires only a handful of training examples, a large language model, and standard web search.

Key facts. Cited by 287 papers in the map (data through 14 Oct 2026). Builds on 62 of its 115 references that are in the map. First posted on arXiv 17 Oct 2022.

Builds on

62 of 115 references.

References · 62

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  8. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  9. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  10. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  11. 2019Language Models as Knowledge Bases?cited by 1,936
  12. 2015A large annotated corpus for learning natural language inferencecited by 1,847
38 more
  1. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  2. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  3. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  4. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  5. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  6. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  7. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  8. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  9. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 743
  10. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
  11. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  12. 2020SummEval: Re-evaluating Summarization Evaluationcited by 674
  13. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
  14. 2019ELI5: Long Form Question Answeringcited by 575
  15. 2020Fact or Fiction: Verifying Scientific Claimscited by 554
  16. 2021Large Dual Encoders Are Generalizable Retrieverscited by 456
  17. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 402
  18. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 378
  19. 2017"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detectioncited by 363
  20. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 356
  21. 2022Teaching language models to support answers with verified quotescited by 292
  22. 2021Measuring Attribution in Natural Language Generation Modelscited by 256
  23. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 225
  24. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 200
  25. 2019MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claimscited by 169
  26. 2021Hurdles to Progress in Long-form Question Answeringcited by 167
  27. 2021Constrained Language Models Yield Few-Shot Semantic Parserscited by 163
  28. 2020Open-Domain Question Answering Goes Conversational via Question Rewritingcited by 148
  29. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 138
  30. 2021Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answeringcited by 132
  31. 2021Annotating and Modeling Fine-grained Factuality in Summarizationcited by 131
  32. 2020Factual Error Correction for Abstractive Summarization Modelscited by 108
  33. 2021Decontextualization: Making Sentences Stand-Alonecited by 102
  34. 2017You said that?cited by 99
  35. 2022PEER: A Collaborative Language Modelcited by 86
  36. 2018Guiding Neural Machine Translation with Retrieved Translation Piecescited by 63
  37. 2021The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpuscited by 60
  38. 2022Dialog Inpainting: Turning Documents into Dialogscited by 56

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 62; 2024: 124; 2025: 43; 2026: 57.

287 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  2. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  3. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  4. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  5. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  6. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
  7. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 324
  8. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  9. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
  10. 2024Knowledge Conflicts for LLMs: A Surveycited by 283
  11. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 269
  12. 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 259
38 more
  1. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 257
  2. 2024LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinationscited by 244
  3. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 240
  4. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 238
  5. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 208
  6. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 206
  7. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 157
  8. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 156
  9. 2024Fine-grained Hallucination Detection and Editing for Language Modelscited by 149
  10. 2023AutoMix: Automatically Mixing Language Modelscited by 125
  11. 2023Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselvescited by 123
  12. 2023WiCE: Real-World Entailment for Claims in Wikipediacited by 120
  13. 2022Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Modelscited by 112
  14. 2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
  15. 2024Critique-out-Loud Reward Modelscited by 106
  16. 2023A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directionscited by 105
  17. 2024A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Modelscited by 100
  18. 2024ContextCite: Attributing Model Generation to Contextcited by 98
  19. 2023ExpertQA: Expert-Curated Questions and Attributed Answerscited by 97
  20. 2024O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?cited by 92
  21. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 91
  22. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  23. 2023Answering Questions by Meta-Reasoning over Multiple Chains of Thoughtcited by 87
  24. 2024Unfamiliar Finetuning Examples Control How Language Models Hallucinatecited by 87
  25. 2023Cognitive Mirage: A Review of Hallucinations in Large Language Modelscited by 84
  26. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  27. 2024LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QAcited by 81
  28. 2023Automatic Evaluation of Attribution by Large Language Modelscited by 72
  29. 2023Large Language Models and Knowledge Graphs: Opportunities and Challengescited by 71
  30. 2023A Survey of Large Language Models Attributioncited by 71
  31. 2023Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofittingcited by 70
  32. 2023WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipediacited by 67
  33. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 66
  34. 2024TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarizationcited by 66
  35. 2023Inference with Reference: Lossless Acceleration of Large Language Modelscited by 65
  36. 2024A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chainscited by 65
  37. 2024Building Guardrails for Large Language Modelscited by 65
  38. 2023Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Taskscited by 64

50 most cited of 287 All 287 (JSON)