# xList-Hate: A Checklist-Based Framework for Interpretable and Generalizable Hate Speech Detection Source: [xList-Hate: A Checklist-Based Framework for Interpretable and Generalizable Hate Speech Detection]() Collection index: [llms.txt]() Data updated: 2026-02-07T05:00:14.331Z Authors: Adri\\'an Gir\\'on, Pablo Miralles, Javier Huertas-Tato, Sergio D'Antonio, David Camacho Published: 2026-02-05T16:51:56.000Z ## Abstract Hate speech detection is commonly framed as a direct binary classification problem despite being a composite concept defined through multiple interacting factors that vary across legal frameworks, platform policies, and annotation guidelines. As a result, supervised models often overfit dataset-specific definitions and exhibit limited robustness under domain shift and annotation noise. We introduce xList-Hate, a diagnostic framework that decomposes hate speech detection into a checklist of explicit, concept-level questions grounded in widely shared normative criteria. Each question is independently answered by a large language model (LLM), producing a binary diagnostic representation that captures hateful content features without directly predicting the final label. These diagnostic signals are then aggregated by a lightweight, fully interpretable decision tree, yielding transparent and auditable predictions. We evaluate it across multiple hate speech benchmarks and model families, comparing it against zero-shot LLM classification and in-domain supervised fine-tuning. While supervised methods typically maximize in-domain performance, we consistently improves cross-dataset robustness and relative performance under domain shift. In addition, qualitative analysis of disagreement cases provides evidence that the framework can be less sensitive to certain forms of annotation inconsistency and contextual ambiguity. Crucially, the approach enables fine-grained interpretability through explicit decision paths and factor-level analysis. Our results suggest that reframing hate speech detection as a diagnostic reasoning task, rather than a monolithic classification problem, provides a robust, explainable, and extensible alternative for content moderation. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Hate speech classification on ETHOS (test)](): Hate speech classification; Ethos (test); AUC: 0.912. - [Hate speech classification on HateCheck (test)](): Hate speech classification; HateCheck (test); AUC: 95.6. - [Hate speech classification on Measuring Hate Speech (MHS) (test)](): Hate speech classification; Measuring Hate Speech (MHS) (test); AUC: 0.819. - [Hate speech classification on Stormfront (test)](): Hate speech classification; Stormfront (test); AUC: 0.921. - [Hate Speech Detection on HateXplain (test)](): Hate Speech Detection; HateXplain (test); Macro F1 Score: not recorded. ## Original sources and implementation [Original paper]() [PDF]()