@inproceedings{amballa-etal-2026-voyager,
title = "{VOYAGER}: A Training Free Approach for Generating Diverse Datasets using {LLM}s",
author = "Amballa, Avinash and
Saidutta, Yashas Malur and
Lin, Chi-Heng and
Kulkarni, Vivek and
Chappidi, Srinivas",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.784/",
pages = "17224--17245",
ISBN = "979-8-89176-390-6",
abstract = "Large language models (LLMs) are increasingly being used to generate synthetic datasets for the evaluation and training of downstream models. However, prior work has noted that such generated data lacks diversity. In this paper, we propose VOYAGER, a novel principled approach to generate diverse datasets. Our approach is iterative and directly optimizes a mathematical quantity that optimizes the diversity of the dataset using the machinery of determinantal point processes. Furthermore, our approach is training-free, applicable to closed-source models, and scalable. In addition to providing theoretical justification for the working of our method, we also demonstrate through comprehensive experiments that VOYAGER improves diversity by $\mathbf{1.5}$-$\mathbf{3}$ times compared to popular baseline approaches."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amballa-etal-2026-voyager">
<titleInfo>
<title>VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Avinash</namePart>
<namePart type="family">Amballa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yashas</namePart>
<namePart type="given">Malur</namePart>
<namePart type="family">Saidutta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chi-Heng</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Kulkarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srinivas</namePart>
<namePart type="family">Chappidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly being used to generate synthetic datasets for the evaluation and training of downstream models. However, prior work has noted that such generated data lacks diversity. In this paper, we propose VOYAGER, a novel principled approach to generate diverse datasets. Our approach is iterative and directly optimizes a mathematical quantity that optimizes the diversity of the dataset using the machinery of determinantal point processes. Furthermore, our approach is training-free, applicable to closed-source models, and scalable. In addition to providing theoretical justification for the working of our method, we also demonstrate through comprehensive experiments that VOYAGER improves diversity by \mathbf1.5-\mathbf3 times compared to popular baseline approaches.</abstract>
<identifier type="citekey">amballa-etal-2026-voyager</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.784/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>17224</start>
<end>17245</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs
%A Amballa, Avinash
%A Saidutta, Yashas Malur
%A Lin, Chi-Heng
%A Kulkarni, Vivek
%A Chappidi, Srinivas
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F amballa-etal-2026-voyager
%X Large language models (LLMs) are increasingly being used to generate synthetic datasets for the evaluation and training of downstream models. However, prior work has noted that such generated data lacks diversity. In this paper, we propose VOYAGER, a novel principled approach to generate diverse datasets. Our approach is iterative and directly optimizes a mathematical quantity that optimizes the diversity of the dataset using the machinery of determinantal point processes. Furthermore, our approach is training-free, applicable to closed-source models, and scalable. In addition to providing theoretical justification for the working of our method, we also demonstrate through comprehensive experiments that VOYAGER improves diversity by \mathbf1.5-\mathbf3 times compared to popular baseline approaches.
%U https://aclanthology.org/2026.acl-long.784/
%P 17224-17245
Markdown (Informal)
[VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs](https://aclanthology.org/2026.acl-long.784/) (Amballa et al., ACL 2026)
ACL
- Avinash Amballa, Yashas Malur Saidutta, Chi-Heng Lin, Vivek Kulkarni, and Srinivas Chappidi. 2026. VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 17224–17245, San Diego, California, United States. Association for Computational Linguistics.