LLMsAgainstHate @ NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs

TL;DR

This paper introduces a parameter-efficient fine-tuning method for large language models to detect hate speech and identify targets in Devanagari-scripted languages like Hindi and Nepali, addressing resource scarcity issues.

Contribution

It presents a novel PEFT approach tailored for hate speech detection in Devanagari languages, demonstrating effectiveness on a new annotated dataset.

Findings

Effective hate speech detection in Hindi and Nepali

PEFT outperforms traditional fine-tuning methods

Resource-efficient approach suitable for low-resource languages

Abstract

The detection of hate speech has become increasingly important in combating online hostility and its real-world consequences. Despite recent advancements, there is limited research addressing hate speech detection in Devanagari-scripted languages, where resources and tools are scarce. While large language models (LLMs) have shown promise in language-related tasks, traditional fine-tuning approaches are often infeasible given the size of the models. In this paper, we propose a Parameter Efficient Fine tuning (PEFT) based solution for hate speech detection and target identification. We evaluate multiple LLMs on the Devanagari dataset provided by (Thapa et al., 2025), which contains annotated instances in 2 languages - Hindi and Nepali. The results demonstrate the efficacy of our approach in handling Devanagari-scripted content.