# Logic2Text: High-Fidelity Natural Language Generation from Logical Forms

arXiv: https://arxiv.org/abs/2004.14579 · HTML: https://mlsanity.com/paper/2004.14579/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 30 of 45)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://mlsanity.com/paper/2201.05966/) (2022)
- [Chart-to-Text: A Large-Scale Benchmark for Chart Summarization](https://mlsanity.com/paper/2203.06486/) (2022)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation](https://mlsanity.com/paper/2108.06712/) (2021)
- [OpenCQA: Open-ended Question Answering with Charts](https://mlsanity.com/paper/2210.06628/) (2022)
- [Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks](https://mlsanity.com/paper/2201.09745/) (2022)
- [StructLM: Towards Building Generalist Models for Structured Knowledge Grounding](https://mlsanity.com/paper/2402.16671/) (2024)
- [Logic-Consistency Text Generation from Semantic Parses](https://mlsanity.com/paper/2108.00577/) (2021)
- [Effective Distillation of Table-based Reasoning Ability from LLMs](https://mlsanity.com/paper/2309.13182/) (2023)
- [CABINET: Content Relevance based Noise Reduction for Table Question Answering](https://mlsanity.com/paper/2402.01155/) (2024)
- [TSQA: Tabular Scenario Based Question Answering](https://mlsanity.com/paper/2101.11429/) (2021)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation](https://mlsanity.com/paper/2205.12697/) (2022)
- [Summaries as Captions: Generating Figure Captions for Scientific Documents with Automated Text Summarization](https://mlsanity.com/paper/2302.12324/) (2023)
- [How Does In-Context Learning Help Prompt Tuning?](https://mlsanity.com/paper/2302.11521/) (2023)
- [Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogs](https://mlsanity.com/paper/2305.12191/) (2023)
- [Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges](https://mlsanity.com/paper/2508.00217/) (2025)
- [LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control](https://mlsanity.com/paper/2302.02962/) (2023)
- [The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding](https://mlsanity.com/paper/2209.07800/) (2022)
- [MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation](https://mlsanity.com/paper/2212.08607/) (2022)
- [TabGenie: A Toolkit for Table-to-Text Generation](https://mlsanity.com/paper/2302.14169/) (2023)
- [Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework](https://mlsanity.com/paper/2212.10097/) (2022)
- [PixT3: Pixel-based Table-To-Text Generation](https://mlsanity.com/paper/2311.09808/) (2023)
- [LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training](https://mlsanity.com/paper/2112.01404/) (2021)
- [Realistic Data Augmentation Framework for Enhancing Tabular Reasoning](https://mlsanity.com/paper/2210.12795/) (2022)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)
- [StructText: A Synthetic Table-to-Text Approach for Benchmark Generation with Multi-Dimensional Evaluation](https://mlsanity.com/paper/2507.21340/) (2025)
- [Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation](https://mlsanity.com/paper/2112.06240/) (2021)
- [Leveraging Data Recasting to Enhance Tabular Reasoning](https://mlsanity.com/paper/2211.12641/) (2022)

## Abstract (arXiv)

Previous works on Natural Language Generation (NLG) from structured data have primarily focused on surface-level descriptions of record sequences. However, for complex structured data, e.g., multi-row tables, it is often desirable for an NLG system to describe interesting facts from logical inferences across records. If only provided with the table, it is hard for existing models to produce controllable and high-fidelity logical generations. In this work, we formulate logical level NLG as generation from logical forms in order to obtain controllable, high-fidelity, and faithful generations. We present a new large-scale dataset, textscLogic2Text, with 10,753 descriptions involving common logic types paired with the underlying logical forms. The logical forms show diversified graph structure of free schema, which poses great challenges on the model's ability to understand the semantics. We experiment on (1) Fully-supervised training with the full datasets, and (2) Few-shot setting, provided with hundreds of paired examples; We compare several popular generation models and analyze their performances. We hope our dataset can encourage research towards building an advanced NLG system capable of natural, faithful, and human-like generation. The dataset and code are available at https://github.com/czyssrs/Logic2Text.