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

arXiv: https://arxiv.org/abs/2404.04103 · HTML: https://mlsanity.com/paper/2404.04103/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 5 Apr 2024.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [ToTTo: A Controlled Table-To-Text Generation Dataset](https://mlsanity.com/paper/2004.14373/) (2020)
- [The E2E Dataset: New Challenges For End-to-End Generation](https://mlsanity.com/paper/1706.09254/) (2017)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation](https://mlsanity.com/paper/2005.03642/) (2020)
- [Handling Divergent Reference Texts when Evaluating Table-to-Text Generation](https://mlsanity.com/paper/1906.01081/) (2019)
- [Data-to-Text Generation with Content Selection and Planning](https://mlsanity.com/paper/1809.00582/) (2018)
- [Text-to-Text Pre-Training for Data-to-Text Tasks](https://mlsanity.com/paper/2005.10433/) (2020)
- [Logical Natural Language Generation from Open-Domain Tables](https://mlsanity.com/paper/2004.10404/) (2020)
- [Semantic Noise Matters for Neural Natural Language Generation](https://mlsanity.com/paper/1911.03905/) (2019)
- [How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings](https://mlsanity.com/paper/2305.11853/) (2023)
- [Plan-then-Generate: Controlled Data-to-Text Generation via Planning](https://mlsanity.com/paper/2108.13740/) (2021)
- [Logic2Text: High-Fidelity Natural Language Generation from Logical Forms](https://mlsanity.com/paper/2004.14579/) (2020)
- [Controlling Hallucinations at Word Level in Data-to-Text Generation](https://mlsanity.com/paper/2102.02810/) (2021)
- [A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systems](https://mlsanity.com/paper/2011.03992/) (2020)
- [Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning](https://mlsanity.com/paper/2205.03972/) (2022)
- [A Hierarchical Model for Data-to-Text Generation](https://mlsanity.com/paper/1912.10011/) (2019)
- [Underreporting of errors in NLG output, and what to do about it](https://mlsanity.com/paper/2108.01182/) (2021)
- [An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing](https://mlsanity.com/paper/2309.08008/) (2023)
- [Making effective use of healthcare data using data-to-text technology](https://mlsanity.com/paper/1808.03507/) (2018)
- [Improving User Controlled Table-To-Text Generation Robustness](https://mlsanity.com/paper/2302.09820/) (2023)
- [Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach](https://mlsanity.com/paper/2301.02071/) (2023)

## Built on by (most cited first, 3 of 3)

- [Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges](https://mlsanity.com/paper/2508.00217/) (2025)
- [Input Matters: Evaluating Input Structure's Impact on LLM Summaries of Sports Play-by-Play](https://mlsanity.com/paper/2510.21034/) (2025)
- [Frame-Guided Synthetic Claim Generation for Automatic Fact-Checking Using High-Volume Tabular Data](https://mlsanity.com/paper/2601.17232/) (2026)

## 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.