@inproceedings{aguiar-etal-2026-geological,
title = "Geological Text Summarization Using Generative Large Language Models",
author = "Aguiar, Matheus Stein de and
Nunes, Rafael Oleques and
Balreira, Dennis Giovani",
editor = "Souza, Marlo and
de-Dios-Flores, Iria and
Santos, Diana and
Freitas, Larissa and
Souza, Jackson Wilke da Cruz and
Ribeiro, Eug{\'e}nio",
booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
month = apr,
year = "2026",
address = "Salvador, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.propor-1.11/",
pages = "111--119",
ISBN = "979-8-89176-387-6",
abstract = "Large generative language models have demonstrated impressive performance in various Natural Language Processing (NLP) tasks. However, the geological domain presents unique challenges for NLP due to its specialized language, which is full of technical terms. Therefore, pre-trained language models on generic corpora may not be suitable for performing geological domain-specific tasks. This article compares several models to identify those with the best performance in the Portuguese geological domain for a text summarization task. We applied the models to a Revista Geologia USP dataset. The dataset consists of abstracts of scientific texts and their respective titles, which we aim for the models to approximate with the summarization task. We tested the models in various scenarios, providing examples or not, and at two temperature levels. We then evaluated the models' performance using quantitative metrics and a brief qualitative analysis comparing the titles proposed by the models with the original title. The results show that the Gemma3:27b model was better in some scenarios, while the Llama3:8b model performed best in others."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aguiar-etal-2026-geological">
<titleInfo>
<title>Geological Text Summarization Using Generative Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matheus</namePart>
<namePart type="given">Stein</namePart>
<namePart type="given">de</namePart>
<namePart type="family">Aguiar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">Oleques</namePart>
<namePart type="family">Nunes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dennis</namePart>
<namePart type="given">Giovani</namePart>
<namePart type="family">Balreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marlo</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iria</namePart>
<namePart type="family">de-Dios-Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larissa</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jackson</namePart>
<namePart type="given">Wilke</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Cruz</namePart>
<namePart type="family">Souza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Salvador, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-387-6</identifier>
</relatedItem>
<abstract>Large generative language models have demonstrated impressive performance in various Natural Language Processing (NLP) tasks. However, the geological domain presents unique challenges for NLP due to its specialized language, which is full of technical terms. Therefore, pre-trained language models on generic corpora may not be suitable for performing geological domain-specific tasks. This article compares several models to identify those with the best performance in the Portuguese geological domain for a text summarization task. We applied the models to a Revista Geologia USP dataset. The dataset consists of abstracts of scientific texts and their respective titles, which we aim for the models to approximate with the summarization task. We tested the models in various scenarios, providing examples or not, and at two temperature levels. We then evaluated the models’ performance using quantitative metrics and a brief qualitative analysis comparing the titles proposed by the models with the original title. The results show that the Gemma3:27b model was better in some scenarios, while the Llama3:8b model performed best in others.</abstract>
<identifier type="citekey">aguiar-etal-2026-geological</identifier>
<location>
<url>https://aclanthology.org/2026.propor-1.11/</url>
</location>
<part>
<date>2026-04</date>
<extent unit="page">
<start>111</start>
<end>119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Geological Text Summarization Using Generative Large Language Models
%A Aguiar, Matheus Stein de
%A Nunes, Rafael Oleques
%A Balreira, Dennis Giovani
%Y Souza, Marlo
%Y de-Dios-Flores, Iria
%Y Santos, Diana
%Y Freitas, Larissa
%Y Souza, Jackson Wilke da Cruz
%Y Ribeiro, Eugénio
%S Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
%D 2026
%8 April
%I Association for Computational Linguistics
%C Salvador, Brazil
%@ 979-8-89176-387-6
%F aguiar-etal-2026-geological
%X Large generative language models have demonstrated impressive performance in various Natural Language Processing (NLP) tasks. However, the geological domain presents unique challenges for NLP due to its specialized language, which is full of technical terms. Therefore, pre-trained language models on generic corpora may not be suitable for performing geological domain-specific tasks. This article compares several models to identify those with the best performance in the Portuguese geological domain for a text summarization task. We applied the models to a Revista Geologia USP dataset. The dataset consists of abstracts of scientific texts and their respective titles, which we aim for the models to approximate with the summarization task. We tested the models in various scenarios, providing examples or not, and at two temperature levels. We then evaluated the models’ performance using quantitative metrics and a brief qualitative analysis comparing the titles proposed by the models with the original title. The results show that the Gemma3:27b model was better in some scenarios, while the Llama3:8b model performed best in others.
%U https://aclanthology.org/2026.propor-1.11/
%P 111-119
Markdown (Informal)
[Geological Text Summarization Using Generative Large Language Models](https://aclanthology.org/2026.propor-1.11/) (Aguiar et al., PROPOR 2026)
ACL
- Matheus Stein de Aguiar, Rafael Oleques Nunes, and Dennis Giovani Balreira. 2026. Geological Text Summarization Using Generative Large Language Models. In Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1, pages 111–119, Salvador, Brazil. Association for Computational Linguistics.