mlsanityData to 7 Oct 2026

Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation

arXiv 1910.08684 ↗First posted 19 Oct 2019cs.CLcited by 62

Not on the map. Why?

Abstract (arXiv)

We address the issue of hallucination in data-to-text generation, i.e., reducing the generation of text that is unsupported by the source. We conjecture that hallucination can be caused by an encoder-decoder model generating content phrases without attending to the source; so we propose a confidence score to ensure that the model attends to the source whenever necessary, as well as a variational Bayes training framework that can learn the score from data. Experiments on the WikiBio (Lebretet al., 2016) dataset show that our approach is more faithful to the source than existing state-of-the-art approaches, according to both PARENT score (Dhingra et al., 2019) and human evaluation. We also report strong results on the WebNLG (Gardent et al., 2017) dataset.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2020: 1; 2021: 19; 2022: 9; 2023: 18; 2024: 12; 2025: 3.

62 papers.

Sort:

By area:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  3. 2023Challenges and Applications of Large Language Modelscited by 251
  4. 2021Get Your Vitamin C! Robust Fact Verification with Contrastive Evidencecited by 222
  5. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  6. 2021On Hallucination and Predictive Uncertainty in Conditional Language Generationcited by 176
  7. 2021Hurdles to Progress in Long-form Question Answeringcited by 166
  8. 2021A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generationcited by 137
  9. 2021Annotating and Modeling Fine-grained Factuality in Summarizationcited by 131
  10. 2021Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Groundingcited by 106
  11. 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detectioncited by 96
  12. 2021Evaluating Attribution in Dialogue Systems: The BEGIN Benchmarkcited by 75
38 more
  1. 2023Exposing Attention Glitches with Flip-Flop Language Modelingcited by 74
  2. 2023On the Calibration of Large Language Models and Alignmentcited by 72
  3. 2023Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofittingcited by 70
  4. 2020Text Generation by Learning from Demonstrationscited by 64
  5. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 45
  6. 2022Conditional Generation with a Question-Answering Blueprintcited by 44
  7. 2023Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decodercited by 44
  8. 2024Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Modelscited by 44
  9. 2023SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluationcited by 42
  10. 2021Controlling Hallucinations at Word Level in Data-to-Text Generationcited by 41
  11. 2021Data-to-text Generation with Macro Planningcited by 34
  12. 2024AI Hallucinations: A Misnomer Worth Clarifyingcited by 34
  13. 2023Teaching Language Models to Hallucinate Less with Synthetic Taskscited by 31
  14. 2021Focus Attention: Promoting Faithfulness and Diversity in Summarizationcited by 30
  15. 2024KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detectioncited by 29
  16. 2022Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methodscited by 27
  17. 2023On Diversified Preferences of Large Language Model Alignmentcited by 26
  18. 2021Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric Viewcited by 24
  19. 2021Logic-Consistency Text Generation from Semantic Parsescited by 23
  20. 2022Don't Say What You Don't Know: Improving the Consistency of Abstractive Summarization by Constraining Beam Searchcited by 23
  21. 2021Sketch and Refine: Towards Faithful and Informative Table-to-Text Generationcited by 21
  22. 2022Towards Tracing Factual Knowledge in Language Models Back to the Training Datacited by 21
  23. 2024Language Models in Dialogue: Conversational Maxims for Human-AI Interactionscited by 21
  24. 2021SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasetscited by 18
  25. 2024Towards Reliable Medical Question Answering: Techniques and Challenges in Mitigating Hallucinations in Language Modelscited by 15
  26. 2021DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generationcited by 11
  27. 2021Truth-Conditional Captioning of Time Series Datacited by 11
  28. 2021Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attributioncited by 10
  29. 2021AgreeSum: Agreement-Oriented Multi-Document Summarizationcited by 10
  30. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  31. 2022Generating Full Length Wikipedia Biographies: The Impact of Gender Bias on the Retrieval-Based Generation of Women Biographiescited by 7
  32. 2024The Effects of Hallucinations in Synthetic Training Data for Relation Extractioncited by 7
  33. 2022Query Expansion Using Contextual Clue Sampling with Language Modelscited by 5
  34. 2023Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generationcited by 5
  35. 2025SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generationcited by 5
  36. 2025CLATTER: Comprehensive Entailment Reasoning for Hallucination Detectioncited by 5
  37. 2023Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approachcited by 4
  38. 2023Generating Faithful Text From a Knowledge Graph with Noisy Reference Textcited by 4

50 most cited of 62 All 62 (JSON)