@inproceedings{cabessa-etal-2024-argument,
title = "Argument Mining in {B}io{M}edicine: Zero-Shot, In-Context Learning and Fine-tuning with {LLM}s",
author = "Cabessa, J{\'e}r{\'e}mie and
Hernault, Hugo and
Mushtaq, Umer",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.16/",
pages = "122--131",
ISBN = "979-12-210-7060-6",
abstract = "Argument Mining (AM) aims to extract the complex argumentative structure of a text and Argument Type Classification (ATC) is an essential sub-task of AM. Large Language Models (LLMs) have shown impressive capabilities in most NLP tasks and beyond. However, fine-tuning LLMs can be challenging. In-Context Learning (ICL) has been suggested as a bridging paradigm between training-free and fine-tuning settings for LLMs. In ICL, an LLM is conditioned to solve tasks using a few solved demonstration examples included in its prompt. We focuse on AM in the biomedical AbstRCT dataset. We address ATC using quantized and unquantized LLaMA-3 models through zero-shot learning, in-context learning, and fine-tuning approaches. We introduce a novel ICL strategy that combines {\$}k{\$}NN-based example selection with majority vote ensembling, along with a well-designed fine-tuning strategy for ATC. In zero-shot setting, we show that LLaMA-3 fails to achieve acceptable classification results, suggesting the need for additional training modalities. However, in our ICL training-free setting, LLaMA-3 can leverage relevant information from only a few demonstration examples to achieve very competitive results. Finally, in our fine-tuning setting, LLaMA-3 achieves state-of-the-art performance on ATC task in AbstRCT dataset."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cabessa-etal-2024-argument">
<titleInfo>
<title>Argument Mining in BioMedicine: Zero-Shot, In-Context Learning and Fine-tuning with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jérémie</namePart>
<namePart type="family">Cabessa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="family">Hernault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Umer</namePart>
<namePart type="family">Mushtaq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>Argument Mining (AM) aims to extract the complex argumentative structure of a text and Argument Type Classification (ATC) is an essential sub-task of AM. Large Language Models (LLMs) have shown impressive capabilities in most NLP tasks and beyond. However, fine-tuning LLMs can be challenging. In-Context Learning (ICL) has been suggested as a bridging paradigm between training-free and fine-tuning settings for LLMs. In ICL, an LLM is conditioned to solve tasks using a few solved demonstration examples included in its prompt. We focuse on AM in the biomedical AbstRCT dataset. We address ATC using quantized and unquantized LLaMA-3 models through zero-shot learning, in-context learning, and fine-tuning approaches. We introduce a novel ICL strategy that combines $k$NN-based example selection with majority vote ensembling, along with a well-designed fine-tuning strategy for ATC. In zero-shot setting, we show that LLaMA-3 fails to achieve acceptable classification results, suggesting the need for additional training modalities. However, in our ICL training-free setting, LLaMA-3 can leverage relevant information from only a few demonstration examples to achieve very competitive results. Finally, in our fine-tuning setting, LLaMA-3 achieves state-of-the-art performance on ATC task in AbstRCT dataset.</abstract>
<identifier type="citekey">cabessa-etal-2024-argument</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.16/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>122</start>
<end>131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Argument Mining in BioMedicine: Zero-Shot, In-Context Learning and Fine-tuning with LLMs
%A Cabessa, Jérémie
%A Hernault, Hugo
%A Mushtaq, Umer
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F cabessa-etal-2024-argument
%X Argument Mining (AM) aims to extract the complex argumentative structure of a text and Argument Type Classification (ATC) is an essential sub-task of AM. Large Language Models (LLMs) have shown impressive capabilities in most NLP tasks and beyond. However, fine-tuning LLMs can be challenging. In-Context Learning (ICL) has been suggested as a bridging paradigm between training-free and fine-tuning settings for LLMs. In ICL, an LLM is conditioned to solve tasks using a few solved demonstration examples included in its prompt. We focuse on AM in the biomedical AbstRCT dataset. We address ATC using quantized and unquantized LLaMA-3 models through zero-shot learning, in-context learning, and fine-tuning approaches. We introduce a novel ICL strategy that combines $k$NN-based example selection with majority vote ensembling, along with a well-designed fine-tuning strategy for ATC. In zero-shot setting, we show that LLaMA-3 fails to achieve acceptable classification results, suggesting the need for additional training modalities. However, in our ICL training-free setting, LLaMA-3 can leverage relevant information from only a few demonstration examples to achieve very competitive results. Finally, in our fine-tuning setting, LLaMA-3 achieves state-of-the-art performance on ATC task in AbstRCT dataset.
%U https://aclanthology.org/2024.clicit-1.16/
%P 122-131
Markdown (Informal)
[Argument Mining in BioMedicine: Zero-Shot, In-Context Learning and Fine-tuning with LLMs](https://aclanthology.org/2024.clicit-1.16/) (Cabessa et al., CLiC-it 2024)
ACL