ArC: Argument-Based Consistency in Toxicity Explanations of LLMs

Zenodo (CERN European Organization for Nuclear Research) 2026 Open access

Read full text
Authors: Ramaravind K M, Joanna Roy, Syed Ishtiaque Ahmed, Shion Guha
DOI: 10.5281/zenodo.18652115
Cited by: 0

Abstract

Source code and datasets for the paper 'Argument-Based Consistency in Toxicity Explanations of LLMs' (EACL 2026). ArC measures the extent to which LLMs' free-form toxicity explanations reflect an ideal and logical argumentation process.

Fields of Study & Subjects

Explainable Artificial Intelligence (XAI) Hate Speech and Cyberbullying Detection Ethics and Social Impacts of AI

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
15 February 2026
Language
EN