Meta’s new method helps AI say ‘I don’t know’
A new fine-tuning approach helps large language models retain their ability to express uncertainty, reducing the risk of incorrect outputs.
University of Cambridge, Meta
William F. Shen et al.
Traditional fine-tuning often weakens a model’s ability to indicate uncertainty, increasing the likelihood of hallucinated content. The proposed Sparse Entity-aware Tuning (SEAT) method helps maintain this ability while incorporating new information.
This study highlights a gap in current fine-tuning practices, which can undermine safety-related features in language models. Preserving uncertainty awareness is important for applications in domains where incorrect information can have serious consequences.
SEAT increases memory requirements and training time, which could limit its use in settings with limited resources.
SEAT offers a way to fine-tune language models while keeping their ability to express uncertainty, contributing to safer and more trustworthy AI outputs.
📄 Read the full paper: Don’t Make It Up: Preserving Ignorance Awareness in LLM Fine-Tuning
……Read full article on Tech in Asia
Other
Comments
Leave a comment in Nestia App