mlsanityData to 7 Oct 2026

R2D2: Robust Data-to-Text with Replacement Detection

arXiv 2205.12467 ↗First posted 25 May 2022cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

Unfaithful text generation is a common problem for text generation systems. In the case of Data-to-Text (D2T) systems, the factuality of the generated text is particularly crucial for any real-world applications. We introduce R2D2, a training framework that addresses unfaithful Data-to-Text generation by training a system both as a generator and a faithfulness discriminator with additional replacement detection and unlikelihood learning tasks. To facilitate such training, we propose two methods for sampling unfaithful sentences. We argue that the poor entity retrieval capability of D2T systems is one of the primary sources of unfaithfulness, so in addition to the existing metrics, we further propose NER-based metrics to evaluate the fidelity of D2T generations. Our experimental results show that R2D2 systems could effectively mitigate the unfaithful text generation, and they achieve new state-of-the-art results on FeTaQA, LogicNLG, and ToTTo, all with significant improvements.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 46 of its 62 references that are in the map. First posted on arXiv 25 May 2022.

Builds on

46 of 62 references.

References · 46

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
  5. 2020Longformer: The Long-Document Transformercited by 3,362
  6. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  7. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  8. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  9. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  10. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  11. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  12. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
34 more
  1. 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
  2. 2019Neural Text Generation with Unlikelihood Trainingcited by 489
  3. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 425
  4. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
  5. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 252
  6. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  7. 2017Challenges in Data-to-Document Generationcited by 226
  8. 2022A Contrastive Framework for Neural Text Generationcited by 224
  9. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  10. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  11. 2020A Survey of Evaluation Metrics Used for NLG Systemscited by 164
  12. 2022BRIO: Bringing Order to Abstractive Summarizationcited by 161
  13. 2022Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Textcited by 154
  14. 2017Faithful to the Original: Fact Aware Neural Abstractive Summarizationcited by 141
  15. 2021Annotating and Modeling Fine-grained Factuality in Summarizationcited by 131
  16. 2021SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarizationcited by 131
  17. 2020Evaluating Factuality in Generation with Dependency-level Entailmentcited by 122
  18. 2021CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarizationcited by 120
  19. 2019Handling Divergent Reference Texts when Evaluating Table-to-Text Generationcited by 119
  20. 2016Modeling Coverage for Neural Machine Translationcited by 110
  21. 2019Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Trainingcited by 110
  22. 2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translationcited by 108
  23. 2020Text-to-Text Pre-Training for Data-to-Text Taskscited by 104
  24. 2020Logical Natural Language Generation from Open-Domain Tablescited by 90
  25. 2021Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selectioncited by 75
  26. 2020Contrastive Learning with Adversarial Perturbations for Conditional Text Generationcited by 56
  27. 2020Pre-training Text-to-Text Transformers for Concept-centric Common Sensecited by 42
  28. 2021TaCL: Improving BERT Pre-training with Token-aware Contrastive Learningcited by 32
  29. 2021Sequence Level Contrastive Learning for Text Summarizationcited by 31
  30. 2021DATE: Detecting Anomalies in Text via Self-Supervision of Transformerscited by 25
  31. 2021Logic-Consistency Text Generation from Semantic Parsescited by 23
  32. 2021Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generationcited by 19
  33. 2019Contrastive Multi-document Question Generationcited by 15
  34. 2021Alleviating Exposure Bias via Contrastive Learning for Abstractive Text Summarizationcited by 14

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4; 2024: 0; 2025: 2.

8 papers.

  1. 2022ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examplescited by 29
  2. 2023Investigating Table-to-Text Generation Capabilities of LLMs in Real-World Information Seeking Scenarioscited by 12
  3. 2022Innovations in Neural Data-to-text Generation: A Surveycited by 10
  4. 2023LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Controlcited by 8
  5. 2023QTSumm: Query-Focused Summarization over Tabular Datacited by 4
  6. 2025OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMscited by 4
  7. 2023Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decodingcited by 3
  8. 2025FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluationcited by 1