A Modular Taxonomy for Hate Speech Definitions and Its Impact on Zero-Shot LLM Classification Performance
This work addresses the problem of inconsistent hate speech detection for NLP practitioners and researchers, but it is incremental as it builds on existing definitions and evaluation methods.
The paper tackles the ambiguity in hate speech definitions by creating a taxonomy of 14 conceptual elements and evaluates how different definitions affect zero-shot classification performance of three LLMs on three datasets, finding that definition specificity impacts performance inconsistently across models.
Detecting harmful content is a crucial task in the landscape of NLP applications for Social Good, with hate speech being one of its most dangerous forms. But what do we mean by hate speech, how can we define it, and how does prompting different definitions of hate speech affect model performance? The contribution of this work is twofold. At the theoretical level, we address the ambiguity surrounding hate speech by collecting and analyzing existing definitions from the literature. We organize these definitions into a taxonomy of 14 Conceptual Elements-building blocks that capture different aspects of hate speech definitions, such as references to the target of hate (individual or groups) or of the potential consequences of it. At the experimental level, we employ the collection of definitions in a systematic zero-shot evaluation of three LLMs, on three hate speech datasets representing different types of data (synthetic, human-in-the-loop, and real-world). We find that choosing different definitions, i.e., definitions with a different degree of specificity in terms of encoded elements, impacts model performance, but this effect is not consistent across all architectures.