@inproceedings{maggini-gamallo-otero-2024-leveraging,
title = "Leveraging Advanced Prompting Strategies in {LL}a{MA}3-8{B} for Enhanced Hyperpartisan News Detection",
author = "Maggini, Michele and
Gamallo Otero, Pablo",
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-1.63/",
pages = "531--539",
ISBN = "979-12-210-7060-6",
abstract = "This paper explores advanced prompting strategies for hyperpartisan news detection using the LLaMA3-8b-Instruct model, an open-source LLM developed by Meta AI. We evaluate zero-shot, few-shot, and Chain-of-Thought (CoT) techniques on two datasets: SemEval-2019 Task 4 and a headline-specific corpus. Collaborating with a political science expert, we incorporate domain-specific knowledge and structured reasoning steps into our prompts, particularly for the CoT approach. Our findings reveal that zero-shot prompting, especially with general prompts, consistently outperforms other techniques across both datasets. This unexpected result challenges assumptions about the superiority of few-shot and CoT methods in specialized tasks. We discuss the implications of these findings for ICL in political text analysis and suggest directions for future research in leveraging large language models for nuanced content classification tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maggini-gamallo-otero-2024-leveraging">
<titleInfo>
<title>Leveraging Advanced Prompting Strategies in LLaMA3-8B for Enhanced Hyperpartisan News Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Maggini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Gamallo Otero</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>This paper explores advanced prompting strategies for hyperpartisan news detection using the LLaMA3-8b-Instruct model, an open-source LLM developed by Meta AI. We evaluate zero-shot, few-shot, and Chain-of-Thought (CoT) techniques on two datasets: SemEval-2019 Task 4 and a headline-specific corpus. Collaborating with a political science expert, we incorporate domain-specific knowledge and structured reasoning steps into our prompts, particularly for the CoT approach. Our findings reveal that zero-shot prompting, especially with general prompts, consistently outperforms other techniques across both datasets. This unexpected result challenges assumptions about the superiority of few-shot and CoT methods in specialized tasks. We discuss the implications of these findings for ICL in political text analysis and suggest directions for future research in leveraging large language models for nuanced content classification tasks.</abstract>
<identifier type="citekey">maggini-gamallo-otero-2024-leveraging</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.63/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>531</start>
<end>539</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Advanced Prompting Strategies in LLaMA3-8B for Enhanced Hyperpartisan News Detection
%A Maggini, Michele
%A Gamallo Otero, Pablo
%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 maggini-gamallo-otero-2024-leveraging
%X This paper explores advanced prompting strategies for hyperpartisan news detection using the LLaMA3-8b-Instruct model, an open-source LLM developed by Meta AI. We evaluate zero-shot, few-shot, and Chain-of-Thought (CoT) techniques on two datasets: SemEval-2019 Task 4 and a headline-specific corpus. Collaborating with a political science expert, we incorporate domain-specific knowledge and structured reasoning steps into our prompts, particularly for the CoT approach. Our findings reveal that zero-shot prompting, especially with general prompts, consistently outperforms other techniques across both datasets. This unexpected result challenges assumptions about the superiority of few-shot and CoT methods in specialized tasks. We discuss the implications of these findings for ICL in political text analysis and suggest directions for future research in leveraging large language models for nuanced content classification tasks.
%U https://aclanthology.org/2024.clicit-1.63/
%P 531-539
Markdown (Informal)
[Leveraging Advanced Prompting Strategies in LLaMA3-8B for Enhanced Hyperpartisan News Detection](https://aclanthology.org/2024.clicit-1.63/) (Maggini & Gamallo Otero, CLiC-it 2024)
ACL