mlsanityData to 7 Oct 2026

Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization

arXiv 2109.09784 ↗First posted 30 Aug 2021cs.CLcited by 128

Not on the map. Why?

Abstract (arXiv)

State-of-the-art abstractive summarization systems often generate hallucinations; i.e., content that is not directly inferable from the source text. Despite being assumed incorrect, we find that much hallucinated content is factual, namely consistent with world knowledge. These factual hallucinations can be beneficial in a summary by providing useful background information. In this work, we propose a novel detection approach that separates factual from non-factual hallucinations of entities. Our method utilizes an entity's prior and posterior probabilities according to pre-trained and finetuned masked language models, respectively. Empirical results suggest that our approach vastly outperforms two baselines %in both accuracy and F1 scores and strongly correlates with human judgments. % on factuality classification tasks. Furthermore, we show that our detector, when used as a reward signal in an off-line reinforcement learning (RL) algorithm, significantly improves the factuality of summaries while maintaining the level of abstractiveness.

Key facts. Cited by 128 papers in the map (data through 7 Oct 2026). Builds on 23 of its 30 references that are in the map. First posted on arXiv 30 Aug 2021.

Builds on

23 of 30 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  5. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  6. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  7. 2015Teaching Machines to Read and Comprehendcited by 1,039
  8. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  9. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 578
  10. 2020Asking and Answering Questions to Evaluate the Factual Consistency of Summariescited by 376
  11. 2020FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarizationcited by 292
  12. 2021Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metricscited by 285
11 more
  1. 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 155
  2. 2020Detecting Hallucinated Content in Conditional Neural Sequence Generationcited by 151
  3. 2020On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translationcited by 127
  4. 2020Evaluating Factuality in Generation with Dependency-level Entailmentcited by 122
  5. 2021Entity-level Factual Consistency of Abstractive Text Summarizationcited by 118
  6. 2020Factual Error Correction for Abstractive Summarization Modelscited by 108
  7. 2020Controlled Hallucinations: Learning to Generate Faithfully from Noisy Datacited by 83
  8. 2020Improved Natural Language Generation via Loss Truncationcited by 75
  9. 2020Multi-Fact Correction in Abstractive Text Summarizationcited by 66
  10. 2020Understanding Neural Abstractive Summarization Models via Uncertaintycited by 34
  11. 2020Reducing Quantity Hallucinations in Abstractive Summarizationcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 12; 2023: 44; 2024: 42; 2025: 21; 2026: 8.

128 papers.

Sort:

By area:

  1. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  2. 2023HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Modelscited by 329
  3. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 251
  4. 2024Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMscited by 246
  5. 2023Fine-tuning Language Models for Factualitycited by 219
  6. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  7. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  8. 2024Large Legal Fictions: Profiling Legal Hallucinations in Large Language Modelscited by 144
  9. 2023The Troubling Emergence of Hallucination in Large Language Models -- An Extensive Definition, Quantification, and Prescriptive Remediationscited by 130
  10. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answeringcited by 126
  11. 2023Hallucinations in Large Multilingual Translation Modelscited by 126
  12. 2022Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectorscited by 103
38 more
  1. 2024A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methodscited by 101
  2. 2023Enhancing Uncertainty-Based Hallucination Detection with Stronger Focuscited by 98
  3. 2023SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistencycited by 89
  4. 2024VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Modelscited by 88
  5. 2023Cognitive Mirage: A Review of Hallucinations in Large Language Modelscited by 83
  6. 2023Automatic Evaluation of Attribution by Large Language Modelscited by 70
  7. 2024Lynx: An Open Source Hallucination Evaluation Modelcited by 55
  8. 2023From Sparse to Dense: GPT-4 Summarization with Chain of Density Promptingcited by 52
  9. 2023ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfercited by 49
  10. 2023Detecting and Mitigating Hallucinations in Multilingual Summarisationcited by 48
  11. 2023Distilling Script Knowledge from Large Language Models for Constrained Language Planningcited by 45
  12. 2024Confabulation: The Surprising Value of Large Language Model Hallucinationscited by 42
  13. 2022On Improving Summarization Factual Consistency from Natural Language Feedbackcited by 38
  14. 2024Mechanistic Understanding and Mitigation of Language Model Non-Factual Hallucinationscited by 38
  15. 2024AI Hallucinations: A Misnomer Worth Clarifyingcited by 34
  16. 2024Improving Medical Reasoning through Retrieval and Self-Reflection with Retrieval-Augmented Large Language Modelscited by 34
  17. 2023HallE-Control: Controlling Object Hallucination in Large Multimodal Modelscited by 31
  18. 2023MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarizationcited by 30
  19. 2024Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trendscited by 25
  20. 2024RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Modelscited by 24
  21. 2025The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMscited by 24
  22. 2024Fine-Grained Natural Language Inference Based Faithfulness Evaluation for Diverse Summarisation Taskscited by 23
  23. 2024Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generationcited by 22
  24. 2024On Positional Bias of Faithfulness for Long-form Summarizationcited by 22
  25. 2024A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagationcited by 21
  26. 2022Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarizationcited by 20
  27. 2024Hallucination Detection and Hallucination Mitigation: An Investigationcited by 20
  28. 2023Zero-Resource Hallucination Prevention for Large Language Modelscited by 19
  29. 2023Natural Language Decompositions of Implicit Content Enable Better Text Representationscited by 18
  30. 2023Bias in News Summarization: Measures, Pitfalls and Corporacited by 18
  31. 2025Hallucination Detection in LLMs with Topological Divergence on Attention Graphscited by 18
  32. 2024An Audit on the Perspectives and Challenges of Hallucinations in NLPcited by 17
  33. 2023DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4cited by 16
  34. 2023Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSAcited by 15
  35. 2024Towards Rationality in Language and Multimodal Agents: A Surveycited by 15
  36. 2024Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negationcited by 15
  37. 2024Hallucination Detection in LLMs: Fast and Memory-Efficient Fine-Tuned Modelscited by 15
  38. 2023A Meta-Evaluation of Faithfulness Metrics for Long-Form Hospital-Course Summarizationcited by 14

50 most cited of 128 All 128 (JSON)