mlsanityData to 7 Oct 2026

Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTo

arXiv 2404.04103 ↗First posted 5 Apr 2024cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Neural Table-to-Text models tend to hallucinate, producing texts that contain factual errors. We investigate whether such errors in the output can be traced back to problems with the input. We manually annotated 1,837 texts generated by multiple models in the politics domain of the ToTTo dataset. We identify the input problems that are responsible for many output errors and show that fixing these inputs reduces factual errors by between 52% and 76% (depending on the model). In addition, we observe that models struggle in processing tabular inputs that are structured in a non-standard way, particularly when the input lacks distinct row and column values or when the column headers are not correctly mapped to corresponding values.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 27 of its 44 references that are in the map. First posted on arXiv 5 Apr 2024.

Builds on

27 of 44 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  6. 2020ToTTo: A Controlled Table-To-Text Generation Datasetcited by 267
  7. 2017The E2E Dataset: New Challenges For End-to-End Generationcited by 252
  8. 2017Challenges in Data-to-Document Generationcited by 226
  9. 2021The Curious Case of Hallucinations in Neural Machine Translationcited by 161
  10. 2020On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translationcited by 127
  11. 2019Handling Divergent Reference Texts when Evaluating Table-to-Text Generationcited by 119
  12. 2018Data-to-Text Generation with Content Selection and Planningcited by 106
15 more
  1. 2020Text-to-Text Pre-Training for Data-to-Text Taskscited by 104
  2. 2020Logical Natural Language Generation from Open-Domain Tablescited by 90
  3. 2019Semantic Noise Matters for Neural Natural Language Generationcited by 64
  4. 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 57
  5. 2021Plan-then-Generate: Controlled Data-to-Text Generation via Planningcited by 52
  6. 2020Logic2Text: High-Fidelity Natural Language Generation from Logical Formscited by 45
  7. 2021Controlling Hallucinations at Word Level in Data-to-Text Generationcited by 41
  8. 2020A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systemscited by 34
  9. 2022Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learningcited by 32
  10. 2019A Hierarchical Model for Data-to-Text Generationcited by 20
  11. 2021Underreporting of errors in NLG output, and what to do about itcited by 19
  12. 2023An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processingcited by 19
  13. 2018Making effective use of healthcare data using data-to-text technologycited by 9
  14. 2023Improving User Controlled Table-To-Text Generation Robustnesscited by 6
  15. 2023Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approachcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challengescited by 10
  2. 2025Input Matters: Evaluating Input Structure's Impact on LLM Summaries of Sports Play-by-Playcited by 0
  3. 2026Frame-Guided Synthetic Claim Generation for Automatic Fact-Checking Using High-Volume Tabular Datacited by 0