HateXScore: A Metric Suite for Evaluating Reasoning Quality in Hate Speech Explanations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Yujia, Lee, Roy Ka-Wei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914265673236480
author Hu, Yujia
Lee, Roy Ka-Wei
author_facet Hu, Yujia
Lee, Roy Ka-Wei
contents Hateful speech detection is a key component of content moderation, yet current evaluation frameworks rarely assess why a text is deemed hateful. We introduce \textsf{HateXScore}, a four-component metric suite designed to evaluate the reasoning quality of model explanations. It assesses (i) conclusion explicitness, (ii) faithfulness and causal grounding of quoted spans, (iii) protected group identification (policy-configurable), and (iv) logical consistency among these elements. Evaluated on six diverse hate speech datasets, \textsf{HateXScore} is intended as a diagnostic complement to reveal interpretability failures and annotation inconsistencies that are invisible to standard metrics like Accuracy or F1. Moreover, human evaluation shows strong agreement with \textsf{HateXScore}, validating it as a practical tool for trustworthy and transparent moderation. \textcolor{red}{Disclaimer: This paper contains sensitive content that may be disturbing to some readers.}
format Preprint
id arxiv_https___arxiv_org_abs_2601_13547
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HateXScore: A Metric Suite for Evaluating Reasoning Quality in Hate Speech Explanations
Hu, Yujia
Lee, Roy Ka-Wei
Computation and Language
Artificial Intelligence
Hateful speech detection is a key component of content moderation, yet current evaluation frameworks rarely assess why a text is deemed hateful. We introduce \textsf{HateXScore}, a four-component metric suite designed to evaluate the reasoning quality of model explanations. It assesses (i) conclusion explicitness, (ii) faithfulness and causal grounding of quoted spans, (iii) protected group identification (policy-configurable), and (iv) logical consistency among these elements. Evaluated on six diverse hate speech datasets, \textsf{HateXScore} is intended as a diagnostic complement to reveal interpretability failures and annotation inconsistencies that are invisible to standard metrics like Accuracy or F1. Moreover, human evaluation shows strong agreement with \textsf{HateXScore}, validating it as a practical tool for trustworthy and transparent moderation. \textcolor{red}{Disclaimer: This paper contains sensitive content that may be disturbing to some readers.}
title HateXScore: A Metric Suite for Evaluating Reasoning Quality in Hate Speech Explanations
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.13547