@inproceedings{chakraborty-etal-2025-group,
title = "Group, Embed and Reason: A Hybrid {LLM} and Embedding Framework for Semantic Attribute Alignment",
author = "Chakraborty, Shramona and
Mujumdar, Shashank and
Gupta, Nitin and
Mehta, Sameep and
Kat, Ronen and
Etelis, Itay and
Mahameed, Mohamed and
Guez, Itai and
Tzoref-Brill, Rachel",
editor = "Potdar, Saloni and
Rojas-Barahona, Lina and
Montella, Sebastien",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = nov,
year = "2025",
address = "Suzhou (China)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-industry.120/",
pages = "1703--1710",
ISBN = "979-8-89176-333-3",
abstract = "In enterprise systems, tasks like API integration, ETL pipeline creation, customer record merging, and data consolidation rely on accurately aligning attributes that refer to the same real-world concept but differ across schemas. This semantic attribute alignment is critical for enabling schema unification, reporting, and analytics. The challenge is amplified in schema only settings where no instance data is available due to ambiguous names, inconsistent descriptions, and varied naming conventions.We propose a hybrid, unsupervised framework that combines the contextual reasoning of Large Language Models (LLMs) with the stability of embedding-based similarity and schema grouping to address token limitations and hallucinations. Our method operates solely on metadata and scales to large schemas by grouping attributes and refining LLM outputs through embedding-based enhancement, justification filtering, and ranking. Experiments on real-world healthcare schemas show strong performance, highlighting the effectiveness of the framework in privacy-constrained scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chakraborty-etal-2025-group">
<titleInfo>
<title>Group, Embed and Reason: A Hybrid LLM and Embedding Framework for Semantic Attribute Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shramona</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashank</namePart>
<namePart type="family">Mujumdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameep</namePart>
<namePart type="family">Mehta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronen</namePart>
<namePart type="family">Kat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itay</namePart>
<namePart type="family">Etelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Mahameed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Itai</namePart>
<namePart type="family">Guez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Tzoref-Brill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saloni</namePart>
<namePart type="family">Potdar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lina</namePart>
<namePart type="family">Rojas-Barahona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou (China)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-333-3</identifier>
</relatedItem>
<abstract>In enterprise systems, tasks like API integration, ETL pipeline creation, customer record merging, and data consolidation rely on accurately aligning attributes that refer to the same real-world concept but differ across schemas. This semantic attribute alignment is critical for enabling schema unification, reporting, and analytics. The challenge is amplified in schema only settings where no instance data is available due to ambiguous names, inconsistent descriptions, and varied naming conventions.We propose a hybrid, unsupervised framework that combines the contextual reasoning of Large Language Models (LLMs) with the stability of embedding-based similarity and schema grouping to address token limitations and hallucinations. Our method operates solely on metadata and scales to large schemas by grouping attributes and refining LLM outputs through embedding-based enhancement, justification filtering, and ranking. Experiments on real-world healthcare schemas show strong performance, highlighting the effectiveness of the framework in privacy-constrained scenarios.</abstract>
<identifier type="citekey">chakraborty-etal-2025-group</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.120/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1703</start>
<end>1710</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Group, Embed and Reason: A Hybrid LLM and Embedding Framework for Semantic Attribute Alignment
%A Chakraborty, Shramona
%A Mujumdar, Shashank
%A Gupta, Nitin
%A Mehta, Sameep
%A Kat, Ronen
%A Etelis, Itay
%A Mahameed, Mohamed
%A Guez, Itai
%A Tzoref-Brill, Rachel
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F chakraborty-etal-2025-group
%X In enterprise systems, tasks like API integration, ETL pipeline creation, customer record merging, and data consolidation rely on accurately aligning attributes that refer to the same real-world concept but differ across schemas. This semantic attribute alignment is critical for enabling schema unification, reporting, and analytics. The challenge is amplified in schema only settings where no instance data is available due to ambiguous names, inconsistent descriptions, and varied naming conventions.We propose a hybrid, unsupervised framework that combines the contextual reasoning of Large Language Models (LLMs) with the stability of embedding-based similarity and schema grouping to address token limitations and hallucinations. Our method operates solely on metadata and scales to large schemas by grouping attributes and refining LLM outputs through embedding-based enhancement, justification filtering, and ranking. Experiments on real-world healthcare schemas show strong performance, highlighting the effectiveness of the framework in privacy-constrained scenarios.
%U https://aclanthology.org/2025.emnlp-industry.120/
%P 1703-1710
Markdown (Informal)
[Group, Embed and Reason: A Hybrid LLM and Embedding Framework for Semantic Attribute Alignment](https://aclanthology.org/2025.emnlp-industry.120/) (Chakraborty et al., EMNLP 2025)
ACL
- Shramona Chakraborty, Shashank Mujumdar, Nitin Gupta, Sameep Mehta, Ronen Kat, Itay Etelis, Mohamed Mahameed, Itai Guez, and Rachel Tzoref-Brill. 2025. Group, Embed and Reason: A Hybrid LLM and Embedding Framework for Semantic Attribute Alignment. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1703–1710, Suzhou (China). Association for Computational Linguistics.