# Revisiting Challenges in Data-to-Text Generation with Fact Grounding

arXiv: https://arxiv.org/abs/2001.03830 · HTML: https://mlsanity.com/paper/2001.03830/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2020.

## Built on by (most cited first, 27 of 27)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [Controlling Hallucinations at Word Level in Data-to-Text Generation](https://mlsanity.com/paper/2102.02810/) (2021)
- [SoK: Memorization in General-Purpose Large Language Models](https://mlsanity.com/paper/2310.18362/) (2023)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models](https://mlsanity.com/paper/2407.08039/) (2024)
- [Logic-Consistency Text Generation from Semantic Parses](https://mlsanity.com/paper/2108.00577/) (2021)
- [Language Models in Dialogue: Conversational Maxims for Human-AI Interactions](https://mlsanity.com/paper/2403.15115/) (2024)
- [Who's Who: Large Language Models Meet Knowledge Conflicts in Practice](https://mlsanity.com/paper/2410.15737/) (2024)
- [Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation](https://mlsanity.com/paper/2401.10186/) (2024)
- [On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook](https://mlsanity.com/paper/2307.16680/) (2023)
- [Towards Verifiable Text Generation with Symbolic References](https://mlsanity.com/paper/2311.09188/) (2023)
- [Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling](https://mlsanity.com/paper/2102.03551/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Generation Challenges: Results of the Accuracy Evaluation Shared Task](https://mlsanity.com/paper/2108.05644/) (2021)
- [On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation](https://mlsanity.com/paper/2406.12221/) (2024)
- [Fidelity-Enriched Contrastive Search: Reconciling the Faithfulness-Diversity Trade-Off in Text Generation](https://mlsanity.com/paper/2310.14981/) (2023)
- [Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation](https://mlsanity.com/paper/2310.16964/) (2023)
- [Tackling Hallucinations in Neural Chart Summarization](https://mlsanity.com/paper/2308.00399/) (2023)
- [ChatGPT Incorrectness Detection in Software Reviews](https://mlsanity.com/paper/2403.16347/) (2024)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)
- [Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization](https://mlsanity.com/paper/2502.19127/) (2025)
- [ConceptFormer: Towards Efficient Use of Knowledge-Graph Embeddings in Large Language Models](https://mlsanity.com/paper/2504.07624/) (2025)
- [Neural Data-to-Text Generation Based on Small Datasets: Comparing the Added Value of Two Semi-Supervised Learning Approaches on Top of a Large Language Model](https://mlsanity.com/paper/2207.06839/) (2022)
- [Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approach](https://mlsanity.com/paper/2511.23335/) (2025)
- [Tree-of-Text: A Tree-based Prompting Framework for Table-to-Text Generation in the Sports Domain](https://mlsanity.com/paper/2604.26501/) (2026)

## Abstract (arXiv)

Data-to-text generation models face challenges in ensuring data fidelity by referring to the correct input source. To inspire studies in this area, Wiseman et al. (2017) introduced the RotoWire corpus on generating NBA game summaries from the box- and line-score tables. However, limited attempts have been made in this direction and the challenges remain. We observe a prominent bottleneck in the corpus where only about 60% of the summary contents can be grounded to the boxscore records. Such information deficiency tends to misguide a conditioned language model to produce unconditioned random facts and thus leads to factual hallucinations. In this work, we restore the information balance and revamp this task to focus on fact-grounded data-to-text generation. We introduce a purified and larger-scale dataset, RotoWire-FG (Fact-Grounding), with 50% more data from the year 2017-19 and enriched input tables, hoping to attract more research focuses in this direction. Moreover, we achieve improved data fidelity over the state-of-the-art models by integrating a new form of table reconstruction as an auxiliary task to boost the generation quality.