# From Tables to Quantified Statements: Evaluating LLM Inference Generation through Executable Verification

arXiv: https://arxiv.org/abs/2609.23966 · HTML: https://mlsanity.com/paper/2609.23966/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [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)
- [Logical Natural Language Generation from Open-Domain Tables](https://mlsanity.com/paper/2004.10404/) (2020)
- [Neural data-to-text generation: A comparison between pipeline and end-to-end architectures](https://mlsanity.com/paper/1908.09022/) (2019)
- [Logic2Text: High-Fidelity Natural Language Generation from Logical Forms](https://mlsanity.com/paper/2004.14579/) (2020)
- [Structural Information Preserving for Graph-to-Text Generation](https://mlsanity.com/paper/2102.06749/) (2021)
- [Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View](https://mlsanity.com/paper/2102.08585/) (2021)
- [Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation](https://mlsanity.com/paper/2105.14778/) (2021)
- [An LLM-Based Approach for Insight Generation in Data Analysis](https://mlsanity.com/paper/2503.11664/) (2025)
- [FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation](https://mlsanity.com/paper/2510.13598/) (2025)

## Abstract (arXiv)

LLMs can generate fluent descriptions from tables, but their outputs may remain logically unsupported by the structured data. We introduce STAT-TO-TEXT, a controlled task in which LLMs generate quantified natural language inferences from statistical tables using quantified constructions such as all, some, no, and most. To evaluate these inferences, we use an LLM generated Python checker code which when executed verifies the corresponding truth conditions against the table. We compare four open-weight LLMs across model families and scales, evaluating faithfulness, logical accuracy, table coverage, and diversity. Our results show that model scale and family matter, with the largest model (GPT-OSS-120B) consistently producing the most faithful inferences without sacrificing greater table coverage and quantifier diversity, as opposed to smaller models. These findings are supported by human annotation, which shows that the automated checker closely aligns with human judgments.