mlsanityData to 14 Oct 2026

Generating Benchmarks for Factuality Evaluation of Language Models

arXiv 2307.06908 ↗First posted 13 Jul 2023cs.CL cs.AIcited by 105

Not on the map. Why?

Abstract (arXiv)

Before deploying a language model (LM) within a given domain, it is important to measure its tendency to generate factually incorrect information in that domain. Existing methods for factuality evaluation of LLM generation focus on facts sampled from the LM itself, and thus do not control the set of evaluated facts and might under-represent domain specific or rare facts. We propose FACTOR: Factual Assessment via Corpus TransfORmation, a scalable approach for evaluating LM factuality. FACTOR automatically transforms a factual corpus of interest into a benchmark evaluating an LM's propensity to generate true facts from the corpus vs. similar but incorrect statements. We use our framework to create three benchmarks: Wiki-FACTOR, News-FACTOR and Expert-FACTOR. We show that: (i) our benchmark scores increase with model size and improve when the LM is augmented with retrieval; (ii) benchmark score and perplexity do not always agree on model ranking; (iii) when perplexity and benchmark score disagree, the latter better reflects factuality in open-ended generation, as measured by human annotators. We make our data and code publicly available in https://github.com/AI21Labs/factor.

Key facts. Cited by 105 papers in the map (data through 14 Oct 2026). Builds on 39 of its 59 references that are in the map. First posted on arXiv 13 Jul 2023.

Builds on

39 of 59 references.

References · 39

  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. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  5. 2016Pointer Sentinel Mixture Modelscited by 3,096
  6. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  7. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  8. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,411
  9. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  10. 2019Language Models as Knowledge Bases?cited by 1,936
  11. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  12. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
27 more
  1. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  2. 2019How Can We Know What Language Models Know?cited by 959
  3. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  4. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 900
  5. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 836
  6. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  7. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  8. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 763
  9. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
  10. 2022GPT-NeoX-20B: An Open-Source Autoregressive Language Modelcited by 713
  11. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  12. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  13. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 439
  14. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
  15. 2021Factual Probing Is [MASK]: Learning vs. Learning to Recallcited by 291
  16. 2021Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metricscited by 287
  17. 2021QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarizationcited by 236
  18. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 225
  19. 2022Factuality Enhanced Language Models for Open-Ended Text Generationcited by 202
  20. 2019Challenges in Building Intelligent Open-domain Dialog Systemscited by 147
  21. 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 138
  22. 2018Breaking NLI Systems with Sentences that Require Simple Lexical Inferencescited by 134
  23. 2022Evaluating the Factual Consistency of Large Language Models Through News Summarizationcited by 92
  24. 2021The Factual Inconsistency Problem in Abstractive Text Summarization: A Surveycited by 79
  25. 2021DialFact: A Benchmark for Fact-Checking in Dialoguecited by 62
  26. 2022How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysiscited by 42
  27. 2016How Grammatical is Character-level Neural Machine Translation? Assessing MT Quality with Contrastive Translation Pairscited by 39

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 16; 2024: 49; 2025: 22; 2026: 18.

105 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  2. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  3. 2023DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Modelscited by 376
  4. 2024Corrective Retrieval Augmented Generationcited by 197
  5. 2023Can LLM-Generated Misinformation Be Detected?cited by 177
  6. 2023Sociotechnical Safety Evaluation of Generative AI Systemscited by 157
  7. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 127
  8. 2024Large Language Models Meet NLP: A Surveycited by 103
  9. 2023Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systemscited by 102
  10. 2024A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Modelscited by 100
  11. 2023ExpertQA: Expert-Curated Questions and Attributed Answerscited by 97
  12. 2024TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Spacecited by 91
38 more
  1. 2024Fast Adversarial Attacks on Language Models In One GPU Minutecited by 88
  2. 2023Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkerscited by 87
  3. 2024Factuality of Large Language Models: A Surveycited by 66
  4. 2023Compressing LLMs: The Truth is Rarely Pure and Never Simplecited by 62
  5. 2023Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBenchcited by 54
  6. 2023Resolving Knowledge Conflicts in Large Language Modelscited by 50
  7. 2025Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinationscited by 48
  8. 2025Steering off Course: Reliability Challenges in Steering Language Modelscited by 34
  9. 2024Improving Uncertainty Quantification in Large Language Models via Semantic Embeddingscited by 30
  10. 2023FactCHD: Benchmarking Fact-Conflicting Hallucination Detectioncited by 29
  11. 2024OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMscited by 28
  12. 2025The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMscited by 26
  13. 2023FFT: Towards Harmlessness Evaluation and Analysis for LLMs with Factuality, Fairness, Toxicitycited by 25
  14. 2024Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generationcited by 25
  15. 2024Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selectioncited by 25
  16. 2024ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Modelscited by 25
  17. 2024FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluationcited by 25
  18. 2024Mitigating Large Language Model Hallucination with Faithful Finetuningcited by 24
  19. 2023UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generationcited by 22
  20. 2023Zero-Resource Hallucination Prevention for Large Language Modelscited by 19
  21. 2024Know When To Stop: A Study of Semantic Drift in Text Generationcited by 18
  22. 2024From Single to Multi: How LLMs Hallucinate in Multi-Document Summarizationcited by 17
  23. 2024Compressing Long Context for Enhancing RAG with AMR-based Concept Distillationcited by 16
  24. 2024Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilitiescited by 16
  25. 2024SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Modelscited by 16
  26. 2023ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?cited by 15
  27. 2024SH2: Self-Highlighted Hesitation Helps You Decode More Truthfullycited by 15
  28. 2024DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Modelscited by 15
  29. 2024Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negationcited by 15
  30. 2024DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answeringcited by 14
  31. 2024ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Modelscited by 14
  32. 2024OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMscited by 13
  33. 2025Uncertainty-Aware Fusion: An Ensemble Framework for Mitigating Hallucinations in Large Language Modelscited by 12
  34. 2025Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metricscited by 12
  35. 2024REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropycited by 11
  36. 2024MELODI: Exploring Memory Compression for Long Contextscited by 11
  37. 2024Face4RAG: Factual Consistency Evaluation for Retrieval Augmented Generation in Chinesecited by 10
  38. 2024The Factuality of Large Language Models in the Legal Domaincited by 10

50 most cited of 105 All 105 (JSON)