# Learning to Reason for Text Generation from Scientific Tables

arXiv: https://arxiv.org/abs/2104.08296 · HTML: https://mlsanity.com/paper/2104.08296/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 24 of 24)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance](https://mlsanity.com/paper/1909.02622/) (2019)
- [ToTTo: A Controlled Table-To-Text Generation Dataset](https://mlsanity.com/paper/2004.14373/) (2020)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation](https://mlsanity.com/paper/1703.09902/) (2017)
- [DART: Open-Domain Structured Data Record to Text Generation](https://mlsanity.com/paper/2007.02871/) (2020)
- [Text Generation from Knowledge Graphs with Graph Transformers](https://mlsanity.com/paper/1904.02342/) (2019)
- [Investigating Pretrained Language Models for Graph-to-Text Generation](https://mlsanity.com/paper/2007.08426/) (2020)
- [Logical Natural Language Generation from Open-Domain Tables](https://mlsanity.com/paper/2004.10404/) (2020)
- [Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge](https://mlsanity.com/paper/1901.07931/) (2019)
- [AxCell: Automatic Extraction of Results from Machine Learning Papers](https://mlsanity.com/paper/2004.14356/) (2020)
- [Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue](https://mlsanity.com/paper/1906.07220/) (2019)
- [Findings of the E2E NLG Challenge](https://mlsanity.com/paper/1810.01170/) (2018)
- [Describing a Knowledge Base](https://mlsanity.com/paper/1809.01797/) (2018)
- [Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators](https://mlsanity.com/paper/1805.08352/) (2018)
- [Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization](https://mlsanity.com/paper/1804.07789/) (2018)
- [Can Neural Generators for Dialogue Learn Sentence Planning and Discourse Structuring?](https://mlsanity.com/paper/1809.03015/) (2018)
- [Improving Generalization by Incorporating Coverage in Natural Language Inference](https://mlsanity.com/paper/1909.08940/) (2019)

## Built on by (most cited first, 14 of 14)

- [HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation](https://mlsanity.com/paper/2108.06712/) (2021)
- [Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks](https://mlsanity.com/paper/2201.09745/) (2022)
- [Coherence boosting: When your pretrained language model is not paying enough attention](https://mlsanity.com/paper/2110.08294/) (2021)
- [A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts](https://mlsanity.com/paper/2311.08374/) (2023)
- [SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation](https://mlsanity.com/paper/2110.10774/) (2021)
- [FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining](https://mlsanity.com/paper/2109.07323/) (2021)
- [A Practical Examination of AI-Generated Text Detectors for Large Language Models](https://mlsanity.com/paper/2412.05139/) (2024)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges](https://mlsanity.com/paper/2508.00217/) (2025)
- [TabGenie: A Toolkit for Table-to-Text Generation](https://mlsanity.com/paper/2302.14169/) (2023)
- [Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context](https://mlsanity.com/paper/2112.08616/) (2021)
- [Improving Cross-task Generalization of Unified Table-to-text Models with Compositional Task Configurations](https://mlsanity.com/paper/2212.08780/) (2022)
- [Large-scale factor analysis shows machine intelligence is only partially interpretable](https://mlsanity.com/paper/2609.36515/) (2026)
- [Defensive Writing in GPT Models](https://mlsanity.com/paper/2610.11355/) (2026)

## Abstract (arXiv)

In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions. Describing scientific tables goes beyond the surface realization of the table content and requires reasoning over table values. The unique properties of SciGen are that (1) tables mostly contain numerical values, and (2) the corresponding descriptions require arithmetic reasoning. SciGen is therefore the first dataset that assesses the arithmetic reasoning capabilities of generation models on complex input structures, i.e., tables from scientific articles. We study the effectiveness of state-of-the-art data-to-text generation models on SciGen and evaluate the results using common metrics as well as human evaluation. Our results and analyses show that (a) while humans like to reason for describing scientific tables, the ability of state-of-the-art models is severely limited on this task, (b) while adding more training data improves the results, it is not the solution for reasoning-aware text generation, and (c) one of the main bottlenecks for this task is the lack of proper automatic evaluation metrics. The data, code, and annotations for human evaluation will be available at https://github.com/UKPLab/SciGen. SciGen opens new avenues for future research in reasoning-aware text generation and evaluation.