作者位次 #4/7ACL 2026Poster· Natural Language Processing
Detoxification for LLM : From Dataset Itself
Wei Shao · Yihang Wang · Gao yu Zhu · Ziqiang Cheng · Lei Yu · Jiafeng Guo · Xueqi Cheng
摘要
Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself. Such training-based or controllable decoding approaches cannot completely suppress the model’s inherent toxicity, w...