Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Purohit, Kiran, V, Venktesh, Devalla, Raghuram, Yerragorla, Krishna Mohan, Bhattacharya, Sourangshu, Anand, Avishek
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2411.03877
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915007543902208
author Purohit, Kiran
V, Venktesh
Devalla, Raghuram
Yerragorla, Krishna Mohan
Bhattacharya, Sourangshu
Anand, Avishek
author_facet Purohit, Kiran
V, Venktesh
Devalla, Raghuram
Yerragorla, Krishna Mohan
Bhattacharya, Sourangshu
Anand, Avishek
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2411_03877
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning
Purohit, Kiran
V, Venktesh
Devalla, Raghuram
Yerragorla, Krishna Mohan
Bhattacharya, Sourangshu
Anand, Avishek
Machine Learning
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).
title EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning
topic Machine Learning
url https://arxiv.org/abs/2411.03877