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

arXiv: https://arxiv.org/abs/2402.06549 · HTML: https://mlsanity.com/paper/2402.06549/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 9 Feb 2024.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 8 of 8)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses](https://mlsanity.com/paper/2210.10634/) (2022)
- [ClimateBert: A Pretrained Language Model for Climate-Related Text](https://mlsanity.com/paper/2110.12010/) (2021)
- [Detecting Hate Speech in Social Media](https://mlsanity.com/paper/1712.06427/) (2017)
- [DeepHate: Hate Speech Detection via Multi-Faceted Text Representations](https://mlsanity.com/paper/2103.11799/) (2021)
- [Prompting and Fine-Tuning Open-Sourced Large Language Models for Stance Classification](https://mlsanity.com/paper/2309.13734/) (2023)

## Built on by (most cited first, 1 of 1)

- [Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions](https://mlsanity.com/paper/2604.12138/) (2026)

## Abstract (arXiv)

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