# Automatic Logical Forms improve fidelity in Table-to-Text generation

arXiv: https://arxiv.org/abs/2310.17279 · HTML: https://mlsanity.com/paper/2310.17279/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 26 Oct 2023.

## Builds on (most cited first, 30 of 31)

- [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)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation](https://mlsanity.com/paper/1905.08205/) (2019)
- [Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation](https://mlsanity.com/paper/1703.09902/) (2017)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [Data-to-Text Generation with Content Selection and Planning](https://mlsanity.com/paper/1809.00582/) (2018)
- [Logical Natural Language Generation from Open-Domain Tables](https://mlsanity.com/paper/2004.10404/) (2020)
- [Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation](https://mlsanity.com/paper/1910.08684/) (2019)
- [Learning Neural Templates for Text Generation](https://mlsanity.com/paper/1808.10122/) (2018)
- [HTLM: Hyper-Text Pre-Training and Prompting of Language Models](https://mlsanity.com/paper/2107.06955/) (2021)
- [Table-to-text Generation by Structure-aware Seq2seq Learning](https://mlsanity.com/paper/1711.09724/) (2017)
- [Plan-then-Generate: Controlled Data-to-Text Generation via Planning](https://mlsanity.com/paper/2108.13740/) (2021)
- [Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints](https://mlsanity.com/paper/2005.00969/) (2020)
- [Data-to-text Generation with Entity Modeling](https://mlsanity.com/paper/1906.03221/) (2019)
- [Logic2Text: High-Fidelity Natural Language Generation from Logical Forms](https://mlsanity.com/paper/2004.14579/) (2020)
- [Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity](https://mlsanity.com/paper/2004.06577/) (2020)
- [Human Evaluation and Correlation with Automatic Metrics in Consultation Note Generation](https://mlsanity.com/paper/2204.00447/) (2022)
- [Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence](https://mlsanity.com/paper/2005.01096/) (2020)
- [Order-Planning Neural Text Generation From Structured Data](https://mlsanity.com/paper/1709.00155/) (2017)
- [A Hierarchical Model for Data-to-Text Generation](https://mlsanity.com/paper/1912.10011/) (2019)
- [Improving Truthfulness of Headline Generation](https://mlsanity.com/paper/2005.00882/) (2020)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [Posterior Control of Blackbox Generation](https://mlsanity.com/paper/2005.04560/) (2020)

## Built on by (most cited first, 2 of 2)

- [PixT3: Pixel-based Table-To-Text Generation](https://mlsanity.com/paper/2311.09808/) (2023)
- [Ta-G-T: Subjectivity Capture in Table to Text Generation via RDF Graphs](https://mlsanity.com/paper/2507.19710/) (2025)

## Abstract (arXiv)

Table-to-text systems generate natural language statements from structured data like tables. While end-to-end techniques suffer from low factual correctness (fidelity), a previous study reported gains when using manual logical forms (LF) that represent the selected content and the semantics of the target text. Given the manual step, it was not clear whether automatic LFs would be effective, or whether the improvement came from content selection alone. We present TlT which, given a table and a selection of the content, first produces LFs and then the textual statement. We show for the first time that automatic LFs improve quality, with an increase in fidelity of 30 points over a comparable system not using LFs. Our experiments allow to quantify the remaining challenges for high factual correctness, with automatic selection of content coming first, followed by better Logic-to-Text generation and, to a lesser extent, better Table-to-Logic parsing.