Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Šuppa, Marek, Skala, Daniel, Jašš, Daniela, Sučík, Samuel, Švec, Andrej, Hraška, Peter
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2402.06549
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909100400443392
author Šuppa, Marek
Skala, Daniel
Jašš, Daniela
Sučík, Samuel
Švec, Andrej
Hraška, Peter
author_facet Šuppa, Marek
Skala, Daniel
Jašš, Daniela
Sučík, Samuel
Švec, Andrej
Hraška, Peter
contents This study details our approach for the CASE 2024 Shared Task on Climate Activism Stance and Hate Event Detection, focusing on Hate Speech Detection, Hate Speech Target Identification, and Stance Detection as classification challenges. We explored the capability of Large Language Models (LLMs), particularly GPT-4, in zero- or few-shot settings enhanced by retrieval augmentation and re-ranking for Tweet classification. Our goal was to determine if LLMs could match or surpass traditional methods in this context. We conducted an ablation study with LLaMA for comparison, and our results indicate that our models significantly outperformed the baselines, securing second place in the Target Detection task. The code for our submission is available at https://github.com/NaiveNeuron/bryndza-case-2024
format Preprint
id arxiv_https___arxiv_org_abs_2402_06549
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bryndza at ClimateActivism 2024: Stance, Target and Hate Event Detection via Retrieval-Augmented GPT-4 and LLaMA
Šuppa, Marek
Skala, Daniel
Jašš, Daniela
Sučík, Samuel
Švec, Andrej
Hraška, Peter
Computation and Language
Artificial Intelligence
This study details our approach for the CASE 2024 Shared Task on Climate Activism Stance and Hate Event Detection, focusing on Hate Speech Detection, Hate Speech Target Identification, and Stance Detection as classification challenges. We explored the capability of Large Language Models (LLMs), particularly GPT-4, in zero- or few-shot settings enhanced by retrieval augmentation and re-ranking for Tweet classification. Our goal was to determine if LLMs could match or surpass traditional methods in this context. We conducted an ablation study with LLaMA for comparison, and our results indicate that our models significantly outperformed the baselines, securing second place in the Target Detection task. The code for our submission is available at https://github.com/NaiveNeuron/bryndza-case-2024
title Bryndza at ClimateActivism 2024: Stance, Target and Hate Event Detection via Retrieval-Augmented GPT-4 and LLaMA
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.06549