# CT-Eval: Benchmarking Chinese Text-to-Table Performance in Large Language Models

arXiv: https://arxiv.org/abs/2405.12174 · HTML: https://mlsanity.com/paper/2405.12174/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 20 May 2024.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [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)
- [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://mlsanity.com/paper/2302.10198/) (2023)
- [Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer](https://mlsanity.com/paper/2102.09550/) (2021)
- [A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation](https://mlsanity.com/paper/1810.13243/) (2018)
- [Exploring the Feasibility of ChatGPT for Event Extraction](https://mlsanity.com/paper/2303.03836/) (2023)
- [Text-to-Table: A New Way of Information Extraction](https://mlsanity.com/paper/2109.02707/) (2021)
- [Table-to-Text: Describing Table Region with Natural Language](https://mlsanity.com/paper/1805.11234/) (2018)
- [A Sequence-to-Sequence&Set Model for Text-to-Table Generation](https://mlsanity.com/paper/2306.00137/) (2023)
- [STable: Table Generation Framework for Encoder-Decoder Models](https://mlsanity.com/paper/2206.04045/) (2022)

## Built on by (most cited first, 1 of 1)

- [Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction](https://mlsanity.com/paper/2507.16271/) (2025)

## Abstract (arXiv)

Text-to-Table aims to generate structured tables to convey the key information from unstructured documents. Existing text-to-table datasets are typically oriented English, limiting the research in non-English languages. Meanwhile, the emergence of large language models (LLMs) has shown great success as general task solvers in multi-lingual settings (e.g., ChatGPT), theoretically enabling text-to-table in other languages. In this paper, we propose a Chinese text-to-table dataset, CT-Eval, to benchmark LLMs on this task. Our preliminary analysis of English text-to-table datasets highlights two key factors for dataset construction: data diversity and data hallucination. Inspired by this, the CT-Eval dataset selects a popular Chinese multidisciplinary online encyclopedia as the source and covers 28 domains to ensure data diversity. To minimize data hallucination, we first train an LLM to judge and filter out the task samples with hallucination, then employ human annotators to clean the hallucinations in the validation and testing sets. After this process, CT-Eval contains 88.6K task samples. Using CT-Eval, we evaluate the performance of open-source and closed-source LLMs. Our results reveal that zero-shot LLMs (including GPT-4) still have a significant performance gap compared with human judgment. Furthermore, after fine-tuning, open-source LLMs can significantly improve their text-to-table ability, outperforming GPT-4 by a large margin. In short, CT-Eval not only helps researchers evaluate and quickly understand the Chinese text-to-table ability of existing LLMs but also serves as a valuable resource to significantly improve the text-to-table performance of LLMs.