@inproceedings{sultania-etal-2025-routenator,
title = "{R}oute{N}ator: A Router-Based Multi-Modal Architecture for Generating Synthetic Training Data for Function Calling {LLM}s",
author = "Belavadi, Vibha and
Vatsa, Tushar and
Sultania, Dewang and
Suresha, Suhas and
Verma, Ishita and
Chen, Cheng and
King, Tracy Holloway and
Friedrich, Michael",
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-1.10/",
doi = "10.18653/v1/2025.knowledgenlp-1.10",
pages = "129--140",
ISBN = "979-8-89176-229-9",
abstract = "This paper addresses fine-tuning Large Language Models (LLMs) for function calling tasks when real user interaction data is unavailable. In digital content creation tools, where users express their needs through natural language queries that must be mapped to API calls, the lack of real-world task-specific data and privacy constraints for training on it necessitate synthetic data generation. Existing approaches to synthetic data generation fall short in diversity and complexity, failing to replicate real-world data distributions and leading to suboptimal performance after LLM fine-tuning. We present a novel router-based architecture that leverages domain resources like content metadata and structured knowledge graphs, along with text-to-text and vision-to-text language models to generate high-quality synthetic training data. Our architecture{'}s flexible routing mechanism enables synthetic data generation that matches observed real-world distributions, addressing a fundamental limitation of traditional approaches. Evaluation on a comprehensive set of real user queries demonstrates significant improvements in both function classification accuracy and API parameter selection. Models fine-tuned with our synthetic data consistently outperform traditional approaches, establishing new benchmarks for function calling tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sultania-etal-2025-routenator">
<titleInfo>
<title>RouteNator: A Router-Based Multi-Modal Architecture for Generating Synthetic Training Data for Function Calling LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vibha</namePart>
<namePart type="family">Belavadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tushar</namePart>
<namePart type="family">Vatsa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dewang</namePart>
<namePart type="family">Sultania</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suhas</namePart>
<namePart type="family">Suresha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ishita</namePart>
<namePart type="family">Verma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tracy</namePart>
<namePart type="given">Holloway</namePart>
<namePart type="family">King</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Friedrich</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>This paper addresses fine-tuning Large Language Models (LLMs) for function calling tasks when real user interaction data is unavailable. In digital content creation tools, where users express their needs through natural language queries that must be mapped to API calls, the lack of real-world task-specific data and privacy constraints for training on it necessitate synthetic data generation. Existing approaches to synthetic data generation fall short in diversity and complexity, failing to replicate real-world data distributions and leading to suboptimal performance after LLM fine-tuning. We present a novel router-based architecture that leverages domain resources like content metadata and structured knowledge graphs, along with text-to-text and vision-to-text language models to generate high-quality synthetic training data. Our architecture’s flexible routing mechanism enables synthetic data generation that matches observed real-world distributions, addressing a fundamental limitation of traditional approaches. Evaluation on a comprehensive set of real user queries demonstrates significant improvements in both function classification accuracy and API parameter selection. Models fine-tuned with our synthetic data consistently outperform traditional approaches, establishing new benchmarks for function calling tasks.</abstract>
<identifier type="citekey">sultania-etal-2025-routenator</identifier>
<identifier type="doi">10.18653/v1/2025.knowledgenlp-1.10</identifier>
<location>
<url>https://aclanthology.org/2025.knowledgenlp-1.10/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>129</start>
<end>140</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RouteNator: A Router-Based Multi-Modal Architecture for Generating Synthetic Training Data for Function Calling LLMs
%A Belavadi, Vibha
%A Vatsa, Tushar
%A Sultania, Dewang
%A Suresha, Suhas
%A Verma, Ishita
%A Chen, Cheng
%A King, Tracy Holloway
%A Friedrich, Michael
%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 sultania-etal-2025-routenator
%X This paper addresses fine-tuning Large Language Models (LLMs) for function calling tasks when real user interaction data is unavailable. In digital content creation tools, where users express their needs through natural language queries that must be mapped to API calls, the lack of real-world task-specific data and privacy constraints for training on it necessitate synthetic data generation. Existing approaches to synthetic data generation fall short in diversity and complexity, failing to replicate real-world data distributions and leading to suboptimal performance after LLM fine-tuning. We present a novel router-based architecture that leverages domain resources like content metadata and structured knowledge graphs, along with text-to-text and vision-to-text language models to generate high-quality synthetic training data. Our architecture’s flexible routing mechanism enables synthetic data generation that matches observed real-world distributions, addressing a fundamental limitation of traditional approaches. Evaluation on a comprehensive set of real user queries demonstrates significant improvements in both function classification accuracy and API parameter selection. Models fine-tuned with our synthetic data consistently outperform traditional approaches, establishing new benchmarks for function calling tasks.
%R 10.18653/v1/2025.knowledgenlp-1.10
%U https://aclanthology.org/2025.knowledgenlp-1.10/
%U https://doi.org/10.18653/v1/2025.knowledgenlp-1.10
%P 129-140
Markdown (Informal)
[RouteNator: A Router-Based Multi-Modal Architecture for Generating Synthetic Training Data for Function Calling LLMs](https://aclanthology.org/2025.knowledgenlp-1.10/) (Belavadi et al., KnowledgeNLP 2025)
ACL
- Vibha Belavadi, Tushar Vatsa, Dewang Sultania, Suhas Suresha, Ishita Verma, Cheng Chen, Tracy Holloway King, and Michael Friedrich. 2025. RouteNator: A Router-Based Multi-Modal Architecture for Generating Synthetic Training Data for Function Calling LLMs. In Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing, pages 129–140, Albuquerque, New Mexico, USA. Association for Computational Linguistics.