@inproceedings{segura-gomez-etal-2025-nlp,
title = "{NLP}-Cimat at {S}em{E}val-2025 Task 11: Prompt Optimization for {LLM}s via Genetic Algorithms and Systematic Mutation applied on Emotion Detection",
author = "Segura-G{\'o}mez, Guillermo and
Lopez Monroy, Adrian Pastor and
Sanchez - Vega, Fernando and
Rosales P{\'e}rez, Alejandro",
editor = "Rosenthal, Sara and
Ros{\'a}, Aiala and
Ghosh, Debanjan and
Zampieri, Marcos",
booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.semeval-1.218/",
pages = "1662--1669",
ISBN = "979-8-89176-273-2",
abstract = "Large Language Models (LLMs) have shown remarkable performance across diverse natural language processing tasks in recent years. However, optimizing instructions to maximize model performance remains a challenge due to the vast search space and the nonlinear relationship between input structure and output quality. This work explores an alternative prompt optimization technique based on genetic algorithms with different structured mutation processes. Unlike traditional random mutations, our method introduces variability in each generation through a guided mutation, enhancing the likelihood of obtaining better prompts for each generation. We apply this approach to emotion detection in the context of SemEval 2025 Task 11, demonstrating the potential to improve prompt efficiency, and consequently task performance. Experimental results show that our method yields competitive results compared to standard optimization techniques while maintaining interpretability and scalability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="segura-gomez-etal-2025-nlp">
<titleInfo>
<title>NLP-Cimat at SemEval-2025 Task 11: Prompt Optimization for LLMs via Genetic Algorithms and Systematic Mutation applied on Emotion Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillermo</namePart>
<namePart type="family">Segura-Gómez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="given">Pastor</namePart>
<namePart type="family">Lopez Monroy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Sanchez - Vega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="family">Rosales Pérez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-273-2</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have shown remarkable performance across diverse natural language processing tasks in recent years. However, optimizing instructions to maximize model performance remains a challenge due to the vast search space and the nonlinear relationship between input structure and output quality. This work explores an alternative prompt optimization technique based on genetic algorithms with different structured mutation processes. Unlike traditional random mutations, our method introduces variability in each generation through a guided mutation, enhancing the likelihood of obtaining better prompts for each generation. We apply this approach to emotion detection in the context of SemEval 2025 Task 11, demonstrating the potential to improve prompt efficiency, and consequently task performance. Experimental results show that our method yields competitive results compared to standard optimization techniques while maintaining interpretability and scalability.</abstract>
<identifier type="citekey">segura-gomez-etal-2025-nlp</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.218/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1662</start>
<end>1669</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP-Cimat at SemEval-2025 Task 11: Prompt Optimization for LLMs via Genetic Algorithms and Systematic Mutation applied on Emotion Detection
%A Segura-Gómez, Guillermo
%A Lopez Monroy, Adrian Pastor
%A Sanchez - Vega, Fernando
%A Rosales Pérez, Alejandro
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F segura-gomez-etal-2025-nlp
%X Large Language Models (LLMs) have shown remarkable performance across diverse natural language processing tasks in recent years. However, optimizing instructions to maximize model performance remains a challenge due to the vast search space and the nonlinear relationship between input structure and output quality. This work explores an alternative prompt optimization technique based on genetic algorithms with different structured mutation processes. Unlike traditional random mutations, our method introduces variability in each generation through a guided mutation, enhancing the likelihood of obtaining better prompts for each generation. We apply this approach to emotion detection in the context of SemEval 2025 Task 11, demonstrating the potential to improve prompt efficiency, and consequently task performance. Experimental results show that our method yields competitive results compared to standard optimization techniques while maintaining interpretability and scalability.
%U https://aclanthology.org/2025.semeval-1.218/
%P 1662-1669
Markdown (Informal)
[NLP-Cimat at SemEval-2025 Task 11: Prompt Optimization for LLMs via Genetic Algorithms and Systematic Mutation applied on Emotion Detection](https://aclanthology.org/2025.semeval-1.218/) (Segura-Gómez et al., SemEval 2025)
ACL