Saved in:
Bibliographic Details
Main Authors: Lopes, Cláudio Lúcio do Val, Machado, Lucca
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.21512
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918354858541056
author Lopes, Cláudio Lúcio do Val
Machado, Lucca
author_facet Lopes, Cláudio Lúcio do Val
Machado, Lucca
contents The concurrent optimization of language models and instructional prompts presents a significant challenge for deploying efficient and effective AI systems, particularly when balancing performance against computational costs like token usage. This paper introduces and assesses a bi-objective evolutionary search engine designed to navigate this complex space, focusing specifically on Small Language Models (SLMs). We employ the NSGA-II algorithm and prompt grammar to simultaneously optimize for task accuracy and token efficiency across some reasoning tasks. Our results successfully identify diverse, high-performing model-prompt combinations, quantitatively revealing the critical trade-off between the two objectives. This research highlights task-specific affinities between particular SLMs and prompt structures (e.g., instructions, context, chain of thought). The generated practical Pareto fronts offer decision-makers a portfolio of optimized solutions adaptable to their specific constraints. This automated approach moves beyond traditional manual tuning, providing a foundational framework for discovering effective human-AI interaction patterns.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21512
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Assessing an evolutionary search engine for small language models, prompts, and evaluation metrics
Lopes, Cláudio Lúcio do Val
Machado, Lucca
Neural and Evolutionary Computing
The concurrent optimization of language models and instructional prompts presents a significant challenge for deploying efficient and effective AI systems, particularly when balancing performance against computational costs like token usage. This paper introduces and assesses a bi-objective evolutionary search engine designed to navigate this complex space, focusing specifically on Small Language Models (SLMs). We employ the NSGA-II algorithm and prompt grammar to simultaneously optimize for task accuracy and token efficiency across some reasoning tasks. Our results successfully identify diverse, high-performing model-prompt combinations, quantitatively revealing the critical trade-off between the two objectives. This research highlights task-specific affinities between particular SLMs and prompt structures (e.g., instructions, context, chain of thought). The generated practical Pareto fronts offer decision-makers a portfolio of optimized solutions adaptable to their specific constraints. This automated approach moves beyond traditional manual tuning, providing a foundational framework for discovering effective human-AI interaction patterns.
title Assessing an evolutionary search engine for small language models, prompts, and evaluation metrics
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2506.21512