Skip to main content

🏢 HPI / University of Potsdam

I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token
·1828 words·9 mins· loading · loading
Natural Language Processing Large Language Models 🏢 HPI / University of Potsdam
Boosting LLM accuracy, a new calibration method using a special [IDK] token explicitly models uncertainty, mitigating hallucinations, and improving factual precision while maintaining knowledge retent…