@inproceedings{nainia-etal-2025-f,
title = "{F}-{L}o{RA}-{QA}: Finetuning {LL}a{MA} Models with Low-Rank Adaptation for {F}rench Botanical Question Generation and Answering",
author = "Nainia, Ayoub and
Vignes-Lebbe, R{\'e}gine and
Mousannif, Hajar and
Zahir, Jihad",
editor = "Angelova, Galia and
Kunilovskaya, Maria and
Escribe, Marie and
Mitkov, Ruslan",
booktitle = "Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.ranlp-1.91/",
pages = "787--796",
abstract = "Despite recent advances in large language models (LLMs), most question-answering (QA) systems remain English-centric and poorly suited to domain-specific scientific texts. This linguistic and domain bias poses a major challenge in botany, where a substantial portion of knowledge is documented in French. We introduce F-LoRA-QA, a fine-tuned LLaMA-based pipeline for French botanical QA, leveraging Low-Rank Adaptation (LoRA) for efficient domain adaptation. We construct a specialized dataset of 16,962 question-answer pairs extracted from scientific flora descriptions and fine-tune LLaMA models to retrieve structured knowledge from unstructured botanical texts. Expert-based evaluation confirms the linguistic quality and domain relevance of generated answers. Compared to baseline LLaMA models, F-LoRA-QA achieves a 300{\%} BLEU score increase, 70{\%} ROUGE-1 F1 gain, +16.8{\%} BERTScore F1, and Exact Match improvement from 2.01{\%} to 23.57{\%}. These results demonstrate the effectiveness of adapting LLMs to low-resource scientific domains and highlight the potential of our approach for automated trait extraction and biodiversity data structuring."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nainia-etal-2025-f">
<titleInfo>
<title>F-LoRA-QA: Finetuning LLaMA Models with Low-Rank Adaptation for French Botanical Question Generation and Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayoub</namePart>
<namePart type="family">Nainia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Régine</namePart>
<namePart type="family">Vignes-Lebbe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hajar</namePart>
<namePart type="family">Mousannif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jihad</namePart>
<namePart type="family">Zahir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
</titleInfo>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Kunilovskaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Escribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite recent advances in large language models (LLMs), most question-answering (QA) systems remain English-centric and poorly suited to domain-specific scientific texts. This linguistic and domain bias poses a major challenge in botany, where a substantial portion of knowledge is documented in French. We introduce F-LoRA-QA, a fine-tuned LLaMA-based pipeline for French botanical QA, leveraging Low-Rank Adaptation (LoRA) for efficient domain adaptation. We construct a specialized dataset of 16,962 question-answer pairs extracted from scientific flora descriptions and fine-tune LLaMA models to retrieve structured knowledge from unstructured botanical texts. Expert-based evaluation confirms the linguistic quality and domain relevance of generated answers. Compared to baseline LLaMA models, F-LoRA-QA achieves a 300% BLEU score increase, 70% ROUGE-1 F1 gain, +16.8% BERTScore F1, and Exact Match improvement from 2.01% to 23.57%. These results demonstrate the effectiveness of adapting LLMs to low-resource scientific domains and highlight the potential of our approach for automated trait extraction and biodiversity data structuring.</abstract>
<identifier type="citekey">nainia-etal-2025-f</identifier>
<location>
<url>https://aclanthology.org/2025.ranlp-1.91/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>787</start>
<end>796</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T F-LoRA-QA: Finetuning LLaMA Models with Low-Rank Adaptation for French Botanical Question Generation and Answering
%A Nainia, Ayoub
%A Vignes-Lebbe, Régine
%A Mousannif, Hajar
%A Zahir, Jihad
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F nainia-etal-2025-f
%X Despite recent advances in large language models (LLMs), most question-answering (QA) systems remain English-centric and poorly suited to domain-specific scientific texts. This linguistic and domain bias poses a major challenge in botany, where a substantial portion of knowledge is documented in French. We introduce F-LoRA-QA, a fine-tuned LLaMA-based pipeline for French botanical QA, leveraging Low-Rank Adaptation (LoRA) for efficient domain adaptation. We construct a specialized dataset of 16,962 question-answer pairs extracted from scientific flora descriptions and fine-tune LLaMA models to retrieve structured knowledge from unstructured botanical texts. Expert-based evaluation confirms the linguistic quality and domain relevance of generated answers. Compared to baseline LLaMA models, F-LoRA-QA achieves a 300% BLEU score increase, 70% ROUGE-1 F1 gain, +16.8% BERTScore F1, and Exact Match improvement from 2.01% to 23.57%. These results demonstrate the effectiveness of adapting LLMs to low-resource scientific domains and highlight the potential of our approach for automated trait extraction and biodiversity data structuring.
%U https://aclanthology.org/2025.ranlp-1.91/
%P 787-796
Markdown (Informal)
[F-LoRA-QA: Finetuning LLaMA Models with Low-Rank Adaptation for French Botanical Question Generation and Answering](https://aclanthology.org/2025.ranlp-1.91/) (Nainia et al., RANLP 2025)
ACL