@inproceedings{berkovitch-etal-2025-generating,
title = "Generating Tables from the Parametric Knowledge of Language Models",
author = "Berkovitch, Yevgeni and
Glickman, Oren and
Somech, Amit and
Wolfson, Tomer",
editor = "Shi, Weijia and
Yu, Wenhao and
Asai, Akari and
Jiang, Meng and
Durrett, Greg and
Hajishirzi, Hannaneh and
Zettlemoyer, Luke",
booktitle = "Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing",
month = may,
year = "2025",
address = "Albuquerque, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.knowledgenlp-1.4/",
doi = "10.18653/v1/2025.knowledgenlp-1.4",
pages = "50--65",
ISBN = "979-8-89176-229-9",
abstract = "We explore generating factual tables from the parametric knowledge of large language models (LLMs). While LLMs have demonstrated impressive capabilities in recreating knowledge bases and generating free-form text, their ability to generate structured tabular data has received little attention. To address this gap, we explore the table generation abilities of eight state-of-the-art LLMs, including GPT-4o and Llama3.1-405B, using three prompting methods: full-table, row-by-row, and cell-by-cell. To facilitate evaluation we introduce WikiTabGen, a new benchmark consisting of 119 manually curated Wikipedia tables and their description. Our findings show that table generation remains challenging, with the best performing model (LLaMA3.1-405B) reaching only 25.4{\%} accuracy. We further analyze how properties like table size, popularity, and numerical content impact performance. This study highlights the unique challenges of LLM-based table generation and offers a foundation for future research in this area. All code, data, and prompts are publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berkovitch-etal-2025-generating">
<titleInfo>
<title>Generating Tables from the Parametric Knowledge of Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yevgeni</namePart>
<namePart type="family">Berkovitch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oren</namePart>
<namePart type="family">Glickman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Somech</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomer</namePart>
<namePart type="family">Wolfson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weijia</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akari</namePart>
<namePart type="family">Asai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannaneh</namePart>
<namePart type="family">Hajishirzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-229-9</identifier>
</relatedItem>
<abstract>We explore generating factual tables from the parametric knowledge of large language models (LLMs). While LLMs have demonstrated impressive capabilities in recreating knowledge bases and generating free-form text, their ability to generate structured tabular data has received little attention. To address this gap, we explore the table generation abilities of eight state-of-the-art LLMs, including GPT-4o and Llama3.1-405B, using three prompting methods: full-table, row-by-row, and cell-by-cell. To facilitate evaluation we introduce WikiTabGen, a new benchmark consisting of 119 manually curated Wikipedia tables and their description. Our findings show that table generation remains challenging, with the best performing model (LLaMA3.1-405B) reaching only 25.4% accuracy. We further analyze how properties like table size, popularity, and numerical content impact performance. This study highlights the unique challenges of LLM-based table generation and offers a foundation for future research in this area. All code, data, and prompts are publicly available.</abstract>
<identifier type="citekey">berkovitch-etal-2025-generating</identifier>
<identifier type="doi">10.18653/v1/2025.knowledgenlp-1.4</identifier>
<location>
<url>https://aclanthology.org/2025.knowledgenlp-1.4/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>50</start>
<end>65</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Tables from the Parametric Knowledge of Language Models
%A Berkovitch, Yevgeni
%A Glickman, Oren
%A Somech, Amit
%A Wolfson, Tomer
%Y Shi, Weijia
%Y Yu, Wenhao
%Y Asai, Akari
%Y Jiang, Meng
%Y Durrett, Greg
%Y Hajishirzi, Hannaneh
%Y Zettlemoyer, Luke
%S Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico, USA
%@ 979-8-89176-229-9
%F berkovitch-etal-2025-generating
%X We explore generating factual tables from the parametric knowledge of large language models (LLMs). While LLMs have demonstrated impressive capabilities in recreating knowledge bases and generating free-form text, their ability to generate structured tabular data has received little attention. To address this gap, we explore the table generation abilities of eight state-of-the-art LLMs, including GPT-4o and Llama3.1-405B, using three prompting methods: full-table, row-by-row, and cell-by-cell. To facilitate evaluation we introduce WikiTabGen, a new benchmark consisting of 119 manually curated Wikipedia tables and their description. Our findings show that table generation remains challenging, with the best performing model (LLaMA3.1-405B) reaching only 25.4% accuracy. We further analyze how properties like table size, popularity, and numerical content impact performance. This study highlights the unique challenges of LLM-based table generation and offers a foundation for future research in this area. All code, data, and prompts are publicly available.
%R 10.18653/v1/2025.knowledgenlp-1.4
%U https://aclanthology.org/2025.knowledgenlp-1.4/
%U https://doi.org/10.18653/v1/2025.knowledgenlp-1.4
%P 50-65
Markdown (Informal)
[Generating Tables from the Parametric Knowledge of Language Models](https://aclanthology.org/2025.knowledgenlp-1.4/) (Berkovitch et al., KnowledgeNLP 2025)
ACL
- Yevgeni Berkovitch, Oren Glickman, Amit Somech, and Tomer Wolfson. 2025. Generating Tables from the Parametric Knowledge of Language Models. In Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing, pages 50–65, Albuquerque, New Mexico, USA. Association for Computational Linguistics.