Optimus mitigates toxicity during LLM fine-tuning by combining repurposed LLM safety alignments for detection with synthetic data and DPO alignment, remaining effective even with highly biased classifiers and against attacks.
Language Model Detoxification in Dialogue with Contextualized Stance Control
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI
Optimus mitigates toxicity during LLM fine-tuning by combining repurposed LLM safety alignments for detection with synthetic data and DPO alignment, remaining effective even with highly biased classifiers and against attacks.