Bryndza at ClimateActivism 2024: Stance, Target and Hate Event Detection via Retrieval-Augmented GPT-4 and LLaMA

TL;DR

This paper investigates the effectiveness of retrieval-augmented GPT-4 and LLaMA models in detecting climate activism stance and hate events in social media, achieving superior performance over baselines.

Contribution

It introduces a retrieval-augmented approach using GPT-4 and LLaMA for stance and hate event detection, demonstrating significant improvements over traditional methods.

Findings

GPT-4 with retrieval augmentation outperformed baselines

LLaMA achieved second place in Target Detection

Models effectively handled zero- and few-shot classification

Abstract

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