Leveraging LLMs for Context-Aware Implicit Textual and Multimodal Hate Speech Detection

arXiv:2510.15685 · cs.CL · Submitted 2025-10-17 · Read on arXiv

cs.CL

Submitted: 2025-10-17

Updated: 2026-09-10

Comments: 8 pages, 9 figures, accepted for publication with the 10th Workshop on Online Abuse and Harms (WOAH) at EMNLP 2026

License: http://creativecommons.org/licenses/by/4.0/

The gist: This paper investigates the use of an LLM to generate auxiliary background context for social media posts, and explores four methods to incorporate this context into the input of an SBERT-based Hate

Terminology

Abstract

This paper investigates the use of an LLM to generate auxiliary background context for social media posts, and explores four methods to incorporate this context into the input of an SBERT-based Hate Speech Detection (HSD) classifier. These are: text concatenation, embedding concatenation, a hierarchical transformer-based fusion, and LLM-driven text enhancement. We evaluate the impact of our context generation and incorporation strategies in a textual setting on the Latent Hatred dataset of implicitly hateful tweets and a multimodal setting on the MAMI dataset of misogynous internet memes. Results are evaluated against a zero-context baseline, two previous approaches based on entity linking, and a zero-shot LLM classifier. Findings indicate that incorporating generated context improves HSD performance by up to 3 and 6 F1 points on textual and multimodal settings respectively, from a zero-context baseline to the highest-performing system, based on embedding concatenation.

Sources

Related papers