@inproceedings{purohit-etal-2024-explora,
title = "{EXPLORA}: Efficient Exemplar Subset Selection for Complex Reasoning",
author = "Purohit, Kiran and
V, Venktesh and
Devalla, Raghuram and
Yerragorla, Krishna Mohan and
Bhattacharya, Sourangshu and
Anand, Avishek",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.307/",
doi = "10.18653/v1/2024.emnlp-main.307",
pages = "5367--5388",
abstract = "Answering reasoning-based complex questions over text and hybrid sources, including tables, is a challenging task. Recent advances in large language models (LLMs) have enabled in-context learning (ICL), allowing LLMs to acquire proficiency in a specific task using only a few demonstration samples (exemplars). A critical challenge in ICL is the selection of optimal exemplars, which can be either task-specific (static) or test-example-specific (dynamic). Static exemplars provide faster inference times and increased robustness across a distribution of test examples. In this paper, we propose an algorithm for static exemplar subset selection for complex reasoning tasks. We introduce EXPLORA, a novel exploration method designed to estimate the parameters of the scoring function, which evaluates exemplar subsets without incorporating confidence information. EXPLORA significantly reduces the number of LLM calls to {\textasciitilde}11{\%} of those required by state-of-the-art methods and achieves a substantial performance improvement of 12.24{\%}. We open-source our code and data (https://github.com/kiranpurohit/EXPLORA)."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="purohit-etal-2024-explora">
<titleInfo>
<title>EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kiran</namePart>
<namePart type="family">Purohit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Venktesh</namePart>
<namePart type="family">V</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghuram</namePart>
<namePart type="family">Devalla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krishna</namePart>
<namePart type="given">Mohan</namePart>
<namePart type="family">Yerragorla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sourangshu</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avishek</namePart>
<namePart type="family">Anand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Answering reasoning-based complex questions over text and hybrid sources, including tables, is a challenging task. Recent advances in large language models (LLMs) have enabled in-context learning (ICL), allowing LLMs to acquire proficiency in a specific task using only a few demonstration samples (exemplars). A critical challenge in ICL is the selection of optimal exemplars, which can be either task-specific (static) or test-example-specific (dynamic). Static exemplars provide faster inference times and increased robustness across a distribution of test examples. In this paper, we propose an algorithm for static exemplar subset selection for complex reasoning tasks. We introduce EXPLORA, a novel exploration method designed to estimate the parameters of the scoring function, which evaluates exemplar subsets without incorporating confidence information. EXPLORA significantly reduces the number of LLM calls to ~11% of those required by state-of-the-art methods and achieves a substantial performance improvement of 12.24%. We open-source our code and data (https://github.com/kiranpurohit/EXPLORA).</abstract>
<identifier type="citekey">purohit-etal-2024-explora</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.307</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.307/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>5367</start>
<end>5388</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning
%A Purohit, Kiran
%A V, Venktesh
%A Devalla, Raghuram
%A Yerragorla, Krishna Mohan
%A Bhattacharya, Sourangshu
%A Anand, Avishek
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F purohit-etal-2024-explora
%X Answering reasoning-based complex questions over text and hybrid sources, including tables, is a challenging task. Recent advances in large language models (LLMs) have enabled in-context learning (ICL), allowing LLMs to acquire proficiency in a specific task using only a few demonstration samples (exemplars). A critical challenge in ICL is the selection of optimal exemplars, which can be either task-specific (static) or test-example-specific (dynamic). Static exemplars provide faster inference times and increased robustness across a distribution of test examples. In this paper, we propose an algorithm for static exemplar subset selection for complex reasoning tasks. We introduce EXPLORA, a novel exploration method designed to estimate the parameters of the scoring function, which evaluates exemplar subsets without incorporating confidence information. EXPLORA significantly reduces the number of LLM calls to ~11% of those required by state-of-the-art methods and achieves a substantial performance improvement of 12.24%. We open-source our code and data (https://github.com/kiranpurohit/EXPLORA).
%R 10.18653/v1/2024.emnlp-main.307
%U https://aclanthology.org/2024.emnlp-main.307/
%U https://doi.org/10.18653/v1/2024.emnlp-main.307
%P 5367-5388
Markdown (Informal)
[EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning](https://aclanthology.org/2024.emnlp-main.307/) (Purohit et al., EMNLP 2024)
ACL
- Kiran Purohit, Venktesh V, Raghuram Devalla, Krishna Mohan Yerragorla, Sourangshu Bhattacharya, and Avishek Anand. 2024. EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 5367–5388, Miami, Florida, USA. Association for Computational Linguistics.