Random paper
 

Computational Story Lab at BLP-2025 Task 1: HateSense: A multi-task learning framework for comprehensive hate speech identification using LLMs

Tabia Tanzin Prama, Christopher M. Danforth, and Peter Sheridan Dodds

Proceedings of the Second Workshop on Bangla Language Processing (BLP-2025), 2025

Times cited: 0

Abstract:

This paper describes HateSense, our multi-task learning framework for the BLP 2025 shared task 1 on Bangla hate speech identification. The task requires not only detecting hate speech but also classifying its type, target, and severity. HateSense integrates binary and multi-label classifiers using both encoder-and decoder-based large language models (LLMs). We experimented with pre-trained encoder models (Bert based models), and decoder models like GPT-4.0, LLaMA 3.1 8B, and Gemma-2 9B. To address challenges such as class imbalance and the linguistic complexity of Bangla, we employed techniques like focal loss and odds ratio preference optimization (ORPO). Experimental results demonstrated that the pre-trained encoders (BanglaBert) achieved state-of-the-art performance. Among different prompting strategies, chain-of-thought (CoT) combined with few-shot prompting proved most effective. Following the HateSense framework, our system attained competitive micro-F1 scores: 0.741 (Task 1A), 0.724 (Task 1B), and 0.7233 (Task 1C). These findings affirm the effectiveness of transformer-based architectures for Bangla hate speech detection and suggest promising avenues for multi-task learning in low-resource languages.
  • This is the default HTML.
  • You can replace it with your own.
  • Include your own code without the HTML, Head, or Body tags.

BibTeX:

@inproceedings{prama2025b,
  author =	 {Prama, Tabia Tanzin and Danforth, Christopher M. and
                  Dodds, P.},
  title =	 {Computational {S}tory {L}ab at {BLP}-2025 {T}ask 1:
                  {H}ate{S}ense: {A} multi-task learning framework for
                  comprehensive hate speech identification using {LLM}s},
  booktitle =	 {Proceedings of the Second Workshop on Bangla
                  Language Processing (BLP-2025)},
  year =	 {2025},
  key =		 {},
  pages =	 {430–442},
  url =		 {https://aclanthology.org/2025.banglalp-1.37/},
}
 
Random paper