mlsanityData to 14 Oct 2026

"According to ...": Prompting Language Models Improves Quoting from Pre-Training Data

arXiv 2305.13252 ↗First posted 22 May 2023cs.CL cs.AIcited by 42

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) may hallucinate and generate fake information, despite pre-training on factual data. Inspired by the journalistic device of "according to sources", we propose according-to prompting: directing LLMs to ground responses against previously observed text. To quantify this grounding, we propose a novel evaluation metric (QUIP-Score) that measures the extent to which model-produced answers are directly found in underlying text corpora. We illustrate with experiments on three corpora (Wikipedia, PubMed, and the U.S. legal tax code) that these prompts improve grounding under our metrics, with the additional benefit of often improving end-task performance. Furthermore, prompts that ask the model to decrease grounding (or to ground to other corpora) indeed decrease QUIP-Score, indicating the ability of LLMs to increase or decrease grounded generations on request.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Builds on 44 of its 63 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

44 of 63 references.

References · 44

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  5. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  6. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  7. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  8. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  9. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,411
  10. 2020Extracting Training Data from Large Language Modelscited by 2,189
  11. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  12. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
32 more
  1. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  2. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  3. 2019PubMedQA: A Dataset for Biomedical Research Question Answeringcited by 1,288
  4. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  5. 2021Deduplicating Training Data Makes Language Models Bettercited by 714
  6. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 699
  7. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  8. 2019ELI5: Long Form Question Answeringcited by 575
  9. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  10. 2021Editing Factual Knowledge in Language Modelscited by 553
  11. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 492
  12. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  13. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  14. 2022Teaching language models to support answers with verified quotescited by 292
  15. 2023TRAK: Attributing Model Behavior at Scalecited by 283
  16. 2023Poisoning Language Models During Instruction Tuningcited by 269
  17. 2021Measuring Attribution in Natural Language Generation Modelscited by 256
  18. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 202
  19. 2021Reframing Instructional Prompts to GPTk's Languagecited by 176
  20. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 173
  21. 2022Rethinking with Retrieval: Faithful Large Language Model Inferencecited by 145
  22. 2023Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4cited by 125
  23. 2022Rationale-Augmented Ensembles in Language Modelscited by 111
  24. 2020A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answeringcited by 62
  25. 2022Read before Generate! Faithful Long Form Question Answering with Machine Readingcited by 47
  26. 2022How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysiscited by 42
  27. 2022Contrastive Learning Reduces Hallucination in Conversationscited by 40
  28. 2022ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Datacited by 34
  29. 2023Data Portraits: Recording Foundation Model Training Datacited by 30
  30. 2020ABNIRML: Analyzing the Behavior of Neural IR Modelscited by 23
  31. 2021Investigating Memorization of Conspiracy Theories in Text Generationcited by 15
  32. 2022Automatic Document Selection for Efficient Encoder Pretrainingcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 23; 2025: 9; 2026: 2.

42 papers.

Sort:

By area:

  1. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  2. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 206
  3. 2023ExpertQA: Expert-Curated Questions and Attributed Answerscited by 97
  4. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  5. 2023Cognitive Mirage: A Review of Hallucinations in Large Language Modelscited by 84
  6. 2023A Survey of Large Language Models Attributioncited by 71
  7. 2024In-context Learning with Retrieved Demonstrations for Language Models: A Surveycited by 70
  8. 2023The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Modelscited by 55
  9. 2024What's Wrong with Your Code Generated by Large Language Models? An Extensive Studycited by 53
  10. 2024Dated Data: Tracing Knowledge Cutoffs in Large Language Modelscited by 51
  11. 2024Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Eracited by 46
  12. 2024Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Modelscited by 40
30 more
  1. 2023Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectificationcited by 38
  2. 2023SoK: Memorization in General-Purpose Large Language Modelscited by 37
  3. 2024Source-Aware Training Enables Knowledge Attribution in Language Modelscited by 30
  4. 2024Undesirable Memorization in Large Language Models: A Surveycited by 29
  5. 2024Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Modelscited by 27
  6. 2024Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answeringcited by 25
  7. 2024Data Contamination Calibration for Black-box LLMscited by 24
  8. 2024AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attributioncited by 23
  9. 2025Metadata Conditioning Accelerates Language Model Pre-trainingcited by 22
  10. 2025Conformal Linguistic Calibration: Trading-off between Factuality and Specificitycited by 20
  11. 2024An Audit on the Perspectives and Challenges of Hallucinations in NLPcited by 17
  12. 2024ALiiCE: Evaluating Positional Fine-grained Citation Generationcited by 15
  13. 2025TokenShapley: Token Level Context Attribution with Shapley Valuecited by 15
  14. 2024Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysiscited by 14
  15. 2024Verifiable by Design: Aligning Language Models to Quote from Pre-Training Datacited by 13
  16. 2025Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Modelscited by 13
  17. 2024DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoningcited by 11
  18. 2024Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphscited by 10
  19. 2025Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Modelscited by 8
  20. 2024Groundedness in Retrieval-augmented Long-form Generation: An Empirical Studycited by 7
  21. 2024Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challengescited by 5
  22. 2023Establishing Trustworthiness: Rethinking Tasks and Model Evaluationcited by 4
  23. 2024Designing an Evaluation Framework for Large Language Models in Astronomy Researchcited by 3
  24. 2025Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Modelscited by 2
  25. 2025SafePassage: High-Fidelity Information Extraction with Black Box LLMscited by 2
  26. 2024Measuring the Groundedness of Legal Question-Answering Systemscited by 1
  27. 2025Bonsai: Interpretable Tree-Adaptive Grounded Reasoningcited by 1
  28. 2025VizTrust: A Visual Analytics Tool for Capturing User Trust Dynamics in Human-AI Communicationcited by 0
  29. 2026MAPLE: Metadata Conditioned LLM Pretraining for Locale-Aware Question Answeringcited by 0
  30. 2026Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Surveycited by 0