@inproceedings{lee-etal-2026-zero,
title = "Zero-Shot Tabular Learning via Hypergraph Reasoning with {LLM}s",
author = "Lee, Geon and
Kim, Kyungho and
Choi, Dongwon and
Kim, Juyeon and
Kang, Shinhwan and
Shin, Kijung",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1822/",
pages = "41521--41536",
ISBN = "979-8-89176-459-0",
abstract = "Tabular data are prevalent across diverse domains such as healthcare and finance. Zero-shot tabular learning aims to make predictions without labeled data. However, existing LLM-based approaches rely on row-wise prompting, resulting in high inference cost and limited use of inter-row dependencies. In this work, we propose TabHGR+, an efficient relation-aware zero-shot framework for tabular data that leverages LLM-generated rules to label and group rows. Specifically, based on column and task descriptions, we use LLMs to generate rules that assign weak labels to all rows. To refine these noisy weak labels, we construct a hypergraph by grouping semantically related rows using LLM-generated rules and perform hypergraph-based label propagation. Lastly, we further enhance the LLM-generated hypergraph for propagation, which is potentially suboptimal, by assigning label-adaptive weights to hyperedges. By requiring only a constant number of LLM calls independent of dataset size, TabHGR+ substantially reduces inference cost while achieving higher classification accuracy than zero-shot and strong few-shot baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2026-zero">
<titleInfo>
<title>Zero-Shot Tabular Learning via Hypergraph Reasoning with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Geon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyungho</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongwon</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juyeon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinhwan</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kijung</namePart>
<namePart type="family">Shin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Tabular data are prevalent across diverse domains such as healthcare and finance. Zero-shot tabular learning aims to make predictions without labeled data. However, existing LLM-based approaches rely on row-wise prompting, resulting in high inference cost and limited use of inter-row dependencies. In this work, we propose TabHGR+, an efficient relation-aware zero-shot framework for tabular data that leverages LLM-generated rules to label and group rows. Specifically, based on column and task descriptions, we use LLMs to generate rules that assign weak labels to all rows. To refine these noisy weak labels, we construct a hypergraph by grouping semantically related rows using LLM-generated rules and perform hypergraph-based label propagation. Lastly, we further enhance the LLM-generated hypergraph for propagation, which is potentially suboptimal, by assigning label-adaptive weights to hyperedges. By requiring only a constant number of LLM calls independent of dataset size, TabHGR+ substantially reduces inference cost while achieving higher classification accuracy than zero-shot and strong few-shot baselines.</abstract>
<identifier type="citekey">lee-etal-2026-zero</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1822/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>41521</start>
<end>41536</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-Shot Tabular Learning via Hypergraph Reasoning with LLMs
%A Lee, Geon
%A Kim, Kyungho
%A Choi, Dongwon
%A Kim, Juyeon
%A Kang, Shinhwan
%A Shin, Kijung
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F lee-etal-2026-zero
%X Tabular data are prevalent across diverse domains such as healthcare and finance. Zero-shot tabular learning aims to make predictions without labeled data. However, existing LLM-based approaches rely on row-wise prompting, resulting in high inference cost and limited use of inter-row dependencies. In this work, we propose TabHGR+, an efficient relation-aware zero-shot framework for tabular data that leverages LLM-generated rules to label and group rows. Specifically, based on column and task descriptions, we use LLMs to generate rules that assign weak labels to all rows. To refine these noisy weak labels, we construct a hypergraph by grouping semantically related rows using LLM-generated rules and perform hypergraph-based label propagation. Lastly, we further enhance the LLM-generated hypergraph for propagation, which is potentially suboptimal, by assigning label-adaptive weights to hyperedges. By requiring only a constant number of LLM calls independent of dataset size, TabHGR+ substantially reduces inference cost while achieving higher classification accuracy than zero-shot and strong few-shot baselines.
%U https://aclanthology.org/2026.emnlp-main.1822/
%P 41521-41536
Markdown (Informal)
[Zero-Shot Tabular Learning via Hypergraph Reasoning with LLMs](https://aclanthology.org/2026.emnlp-main.1822/) (Lee et al., EMNLP 2026)
ACL
- Geon Lee, Kyungho Kim, Dongwon Choi, Juyeon Kim, Shinhwan Kang, and Kijung Shin. 2026. Zero-Shot Tabular Learning via Hypergraph Reasoning with LLMs. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 41521–41536, Budapest, Hungary. Association for Computational Linguistics.