HateMirage: An Explainable Multi-Dimensional Dataset for Decoding Faux Hate and Subtle Online Abuse

TL;DR

HateMirage introduces a multi-dimensional dataset of faux hate comments with annotations on target, intent, and social implications, aiming to improve explainability and reasoning in detecting subtle online hate stemming from misinformation.

Contribution

The paper presents HateMirage, a novel dataset with multi-dimensional annotations for explainable hate speech detection related to fake narratives, filling a gap in existing datasets and benchmarks.

Findings

Model explanation quality depends more on pretraining diversity than scale.

Benchmarking shows current models struggle with multi-dimensional reasoning.

HateMirage enables research on nuanced hate and misinformation interplay.

Abstract

Subtle and indirect hate speech remains an underexplored challenge in online safety research, particularly when harmful intent is embedded within misleading or manipulative narratives. Existing hate speech datasets primarily capture overt toxicity, underrepresenting the nuanced ways misinformation can incite or normalize hate. To address this gap, we present HateMirage, a novel dataset of Faux Hate comments designed to advance reasoning and explainability research on hate emerging from fake or distorted narratives. The dataset was constructed by identifying widely debunked misinformation claims from fact-checking sources and tracing related YouTube discussions, resulting in 4,530 user comments. Each comment is annotated along three interpretable dimensions: Target (who is affected), Intent (the underlying motivation or goal behind the comment), and Implication (its potential social impact). Unlike prior explainability datasets such as HateXplain and HARE, which offer token-level or single-dimensional reasoning, HateMirage introduces a multi-dimensional explanation framework that captures the interplay between misinformation, harm, and social consequence. We benchmark multiple open-source language models on HateMirage using ROUGE-L F1 and Sentence-BERT similarity to assess explanation coherence. Results suggest that explanation quality may depend more on pretraining diversity and reasoning-oriented data rather than on model scale alone. By coupling misinformation reasoning with harm attribution, HateMirage establishes a new benchmark for interpretable hate detection and responsible AI research.