LifeTox: Unveiling Implicit Toxicity in Life Advice
This addresses the need for better implicit toxicity detection in advice-seeking scenarios for AI safety applications, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of detecting implicit toxicity in life advice contexts by introducing LifeTox, a dataset derived from personal experiences through open-ended questions. Experiments show that RoBERTa fine-tuned on LifeTox matches or surpasses the zero-shot performance of large language models in toxicity classification tasks.
As large language models become increasingly integrated into daily life, detecting implicit toxicity across diverse contexts is crucial. To this end, we introduce LifeTox, a dataset designed for identifying implicit toxicity within a broad range of advice-seeking scenarios. Unlike existing safety datasets, LifeTox comprises diverse contexts derived from personal experiences through open-ended questions. Experiments demonstrate that RoBERTa fine-tuned on LifeTox matches or surpasses the zero-shot performance of large language models in toxicity classification tasks. These results underscore the efficacy of LifeTox in addressing the complex challenges inherent in implicit toxicity. We open-sourced the dataset\footnote{\url{https://huggingface.co/datasets/mbkim/LifeTox}} and the LifeTox moderator family; 350M, 7B, and 13B.