@inproceedings{nunes-etal-2026-bones,
title = "From Bones to Rocks: A Systematic Evaluation of Specialized Definition Generation for {P}ortuguese",
author = "Nunes, Rafael Oleques and
Balreira, Dennis Giovani and
Carbonera, Joel Lu{\'i}s",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.302/",
doi = "10.63317/4w8a83i8b3wy",
pages = "3794--3804",
abstract = "This work presents a systematic evaluation of Large Language Models (LLMs) for generating specialized definitions in Portuguese, focusing on the medical and geological domains. We introduce a robust benchmark and employ a rigorous, statistically grounded evaluation framework, including 5-fold cross-validation and significance testing, to ensure the reliability and generalizability of our findings. Our comprehensive experiments with various open-source, decoder-only LLMs explore in-context learning (ICL) with diverse prompting strategies, ranging from zero-shot to few-shot and contextual information. The evaluated models include multilingual architectures and one model that underwent continued pretraining specifically for Portuguese, allowing us to assess the impact of language adaptation on definition generation quality. The results indicate that most evaluated models perform effectively in this task, with relatively small performance differences among the top models. Statistical analyses confirmed that these differences are not consistently significant, suggesting that several open LLMs, regardless of their size, multilingual capacity, or language specialization, offer comparable effectiveness for Portuguese definition generation. These findings provide valuable insights for selecting and adapting models for specialized NLP tasks in low-resource languages like Portuguese."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nunes-etal-2026-bones">
<titleInfo>
<title>From Bones to Rocks: A Systematic Evaluation of Specialized Definition Generation for Portuguese</title>
</titleInfo>
<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>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="given">Luís</namePart>
<namePart type="family">Carbonera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work presents a systematic evaluation of Large Language Models (LLMs) for generating specialized definitions in Portuguese, focusing on the medical and geological domains. We introduce a robust benchmark and employ a rigorous, statistically grounded evaluation framework, including 5-fold cross-validation and significance testing, to ensure the reliability and generalizability of our findings. Our comprehensive experiments with various open-source, decoder-only LLMs explore in-context learning (ICL) with diverse prompting strategies, ranging from zero-shot to few-shot and contextual information. The evaluated models include multilingual architectures and one model that underwent continued pretraining specifically for Portuguese, allowing us to assess the impact of language adaptation on definition generation quality. The results indicate that most evaluated models perform effectively in this task, with relatively small performance differences among the top models. Statistical analyses confirmed that these differences are not consistently significant, suggesting that several open LLMs, regardless of their size, multilingual capacity, or language specialization, offer comparable effectiveness for Portuguese definition generation. These findings provide valuable insights for selecting and adapting models for specialized NLP tasks in low-resource languages like Portuguese.</abstract>
<identifier type="citekey">nunes-etal-2026-bones</identifier>
<identifier type="doi">10.63317/4w8a83i8b3wy</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.302/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3794</start>
<end>3804</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Bones to Rocks: A Systematic Evaluation of Specialized Definition Generation for Portuguese
%A Nunes, Rafael Oleques
%A Balreira, Dennis Giovani
%A Carbonera, Joel Luís
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F nunes-etal-2026-bones
%X This work presents a systematic evaluation of Large Language Models (LLMs) for generating specialized definitions in Portuguese, focusing on the medical and geological domains. We introduce a robust benchmark and employ a rigorous, statistically grounded evaluation framework, including 5-fold cross-validation and significance testing, to ensure the reliability and generalizability of our findings. Our comprehensive experiments with various open-source, decoder-only LLMs explore in-context learning (ICL) with diverse prompting strategies, ranging from zero-shot to few-shot and contextual information. The evaluated models include multilingual architectures and one model that underwent continued pretraining specifically for Portuguese, allowing us to assess the impact of language adaptation on definition generation quality. The results indicate that most evaluated models perform effectively in this task, with relatively small performance differences among the top models. Statistical analyses confirmed that these differences are not consistently significant, suggesting that several open LLMs, regardless of their size, multilingual capacity, or language specialization, offer comparable effectiveness for Portuguese definition generation. These findings provide valuable insights for selecting and adapting models for specialized NLP tasks in low-resource languages like Portuguese.
%R 10.63317/4w8a83i8b3wy
%U https://aclanthology.org/2026.lrec-1.302/
%U https://doi.org/10.63317/4w8a83i8b3wy
%P 3794-3804
Markdown (Informal)
[From Bones to Rocks: A Systematic Evaluation of Specialized Definition Generation for Portuguese](https://aclanthology.org/2026.lrec-1.302/) (Nunes et al., LREC 2026)
ACL