# FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation

arXiv: https://arxiv.org/abs/2510.13598 · HTML: https://mlsanity.com/paper/2510.13598/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Builds on (most cited first, 28 of 28)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [ToTTo: A Controlled Table-To-Text Generation Dataset](https://mlsanity.com/paper/2004.14373/) (2020)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Chart-to-Text: A Large-Scale Benchmark for Chart Summarization](https://mlsanity.com/paper/2203.06486/) (2022)
- [Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks](https://mlsanity.com/paper/2305.10160/) (2023)
- [Task Contamination: Language Models May Not Be Few-Shot Anymore](https://mlsanity.com/paper/2312.16337/) (2023)
- [Logical Natural Language Generation from Open-Domain Tables](https://mlsanity.com/paper/2004.10404/) (2020)
- [Table-GPT: Table-tuned GPT for Diverse Table Tasks](https://mlsanity.com/paper/2310.09263/) (2023)
- [Table-to-text Generation by Structure-aware Seq2seq Learning](https://mlsanity.com/paper/1711.09724/) (2017)
- [How Does Quantization Affect Multilingual LLMs?](https://mlsanity.com/paper/2407.03211/) (2024)
- [Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs](https://mlsanity.com/paper/2307.07312/) (2023)
- [Table-To-Text generation and pre-training with TabT5](https://mlsanity.com/paper/2210.09162/) (2022)
- [Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation](https://mlsanity.com/paper/2401.10186/) (2024)
- [GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents](https://mlsanity.com/paper/2505.11368/) (2025)
- [An LLM-Based Approach for Insight Generation in Data Analysis](https://mlsanity.com/paper/2503.11664/) (2025)
- [Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning](https://mlsanity.com/paper/2410.02631/) (2024)
- [R2D2: Robust Data-to-Text with Replacement Detection](https://mlsanity.com/paper/2205.12467/) (2022)
- [LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control](https://mlsanity.com/paper/2302.02962/) (2023)
- [HeLM: Highlighted Evidence augmented Language Model for Enhanced Table-to-Text Generation](https://mlsanity.com/paper/2311.08896/) (2023)

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

- [From Tables to Quantified Statements: Evaluating LLM Inference Generation through Executable Verification](https://mlsanity.com/paper/2609.23966/) (2026)
- [Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation](https://mlsanity.com/paper/2610.03525/) (2026)

## Abstract (arXiv)

Table-to-text generation (insight generation from tables) is a challenging task that requires precision in analyzing the data. In addition, the evaluation of existing benchmarks is affected by contamination of Large Language Model (LLM) training data as well as domain imbalance. We introduce FreshTab, an on-the-fly table-to-text benchmark generation from Wikipedia, to combat the LLM data contamination problem and enable domain-sensitive evaluation. While non-English table-to-text datasets are limited, FreshTab collects datasets in different languages on demand (we experiment with German, Russian and French in addition to English). We find that insights generated by LLMs from recent tables collected by our method appear clearly worse by automatic metrics, but this does not translate into LLM and human evaluations. Domain effects are visible in all evaluations, showing that a~domain-balanced benchmark is more challenging.