Tag
This survey synthesizes research on toxicity detection and detoxification for multilingual large language models, cataloging threat models, task formulations, detection approaches, and mitigation strategies, while identifying persistent challenges such as uneven language coverage and culturally contingent definitions of harm.
This paper investigates how LLMs' internal priors affect zero-shot annotation performance, finding that nearly two-thirds of errors resist prompt-based correction and introducing Definition-Specific Familiarity as a better predictor than memorization metrics.
The paper introduces CITA, a framework for generating implicit toxicity attacks in Chinese to evaluate and improve LLM toxicity detectors, finding high attack success rates across tested models.
This paper studies fairness in toxicity classification across three axes: ranking, calibration, and abstention. It compares ERM, reweighted ERM, and Group DRO methods with post-hoc interventions, finding that calibration disparity is a hidden fairness violation and that abstention itself can be unfair.
This paper presents a system for the EEUCA 2026 shared task on toxicity detection in gaming chat, achieving 4th place by fine-tuning Llama 3.1 8B with synthetic data augmentation. It highlights a 'validation trap' phenomenon where high validation scores do not correlate with test performance due to dataset distribution shifts.