@inproceedings{khabiri-etal-2025-declarative,
title = "Declarative Techniques for {NL} Queries over Heterogeneous Data",
author = "Khabiri, Elham and
Kephart, Jeffrey O. and
Iii, Fenno F. Heath and
Jayaraman, Srideepika and
Li, Yingjie and
Tipu, Fateh A. and
Shah, Dhruv and
Fokoue, Achille and
Bhamidipaty, Anu",
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.123/",
pages = "1744--1761",
ISBN = "979-8-89176-333-3",
abstract = "In many industrial settings, users wish to ask questions in natural language, the answers to which require assembling information from diverse structured data sources. With the advent of Large Language Models (LLMs), applications can now translate natural language questions into a set of API calls or database calls, execute them, and combine the results into an appropriate natural language response. However, these applications remain impractical in realistic industrial settings because they do not cope with the data source heterogeneity that typifies such environments. In this work, we simulate the heterogeneity of real industry settings by introducing two extensions of the popular Spider benchmark dataset that require a combination of database and API calls. Then, we introduce a declarative approach to handling such data heterogeneityand demonstrate that it copes with data source heterogeneity significantly better than state-of-the-art LLM-based agentic or imperative code generation systems. Our augmented benchmarks are available to the research community."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khabiri-etal-2025-declarative">
<titleInfo>
<title>Declarative Techniques for NL Queries over Heterogeneous Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elham</namePart>
<namePart type="family">Khabiri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeffrey</namePart>
<namePart type="given">O</namePart>
<namePart type="family">Kephart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fenno</namePart>
<namePart type="given">F</namePart>
<namePart type="given">Heath</namePart>
<namePart type="family">Iii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srideepika</namePart>
<namePart type="family">Jayaraman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fateh</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Tipu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhruv</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Achille</namePart>
<namePart type="family">Fokoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anu</namePart>
<namePart type="family">Bhamidipaty</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 many industrial settings, users wish to ask questions in natural language, the answers to which require assembling information from diverse structured data sources. With the advent of Large Language Models (LLMs), applications can now translate natural language questions into a set of API calls or database calls, execute them, and combine the results into an appropriate natural language response. However, these applications remain impractical in realistic industrial settings because they do not cope with the data source heterogeneity that typifies such environments. In this work, we simulate the heterogeneity of real industry settings by introducing two extensions of the popular Spider benchmark dataset that require a combination of database and API calls. Then, we introduce a declarative approach to handling such data heterogeneityand demonstrate that it copes with data source heterogeneity significantly better than state-of-the-art LLM-based agentic or imperative code generation systems. Our augmented benchmarks are available to the research community.</abstract>
<identifier type="citekey">khabiri-etal-2025-declarative</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-industry.123/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>1744</start>
<end>1761</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Declarative Techniques for NL Queries over Heterogeneous Data
%A Khabiri, Elham
%A Kephart, Jeffrey O.
%A Iii, Fenno F. Heath
%A Jayaraman, Srideepika
%A Li, Yingjie
%A Tipu, Fateh A.
%A Shah, Dhruv
%A Fokoue, Achille
%A Bhamidipaty, Anu
%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 khabiri-etal-2025-declarative
%X In many industrial settings, users wish to ask questions in natural language, the answers to which require assembling information from diverse structured data sources. With the advent of Large Language Models (LLMs), applications can now translate natural language questions into a set of API calls or database calls, execute them, and combine the results into an appropriate natural language response. However, these applications remain impractical in realistic industrial settings because they do not cope with the data source heterogeneity that typifies such environments. In this work, we simulate the heterogeneity of real industry settings by introducing two extensions of the popular Spider benchmark dataset that require a combination of database and API calls. Then, we introduce a declarative approach to handling such data heterogeneityand demonstrate that it copes with data source heterogeneity significantly better than state-of-the-art LLM-based agentic or imperative code generation systems. Our augmented benchmarks are available to the research community.
%U https://aclanthology.org/2025.emnlp-industry.123/
%P 1744-1761
Markdown (Informal)
[Declarative Techniques for NL Queries over Heterogeneous Data](https://aclanthology.org/2025.emnlp-industry.123/) (Khabiri et al., EMNLP 2025)
ACL
- Elham Khabiri, Jeffrey O. Kephart, Fenno F. Heath Iii, Srideepika Jayaraman, Yingjie Li, Fateh A. Tipu, Dhruv Shah, Achille Fokoue, and Anu Bhamidipaty. 2025. Declarative Techniques for NL Queries over Heterogeneous Data. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1744–1761, Suzhou (China). Association for Computational Linguistics.