Nov. 20, 2023, 5 p.m. | Alyssa Hughes

Microsoft Research

Lifelong model editing fixes mistakes discovered after model deployment. This work could expand sequential editing to model properties like fairness and privacy and enable a new class of solutions for adapting LLMs over long deployment lifetimes.

The post Lifelong model editing in large language models: Balancing low-cost targeted edits and catastrophic forgetting appeared first on Microsoft Research.

cost deployment editing fairness language language models large language large language models llms low mistakes model deployment privacy research blog solutions work

Software Developer/Data Scientist (RD2/RD3)

@ Argonne National Laboratory | Lemont, IL USA

Global Health Financial Data Analyst

@ Guidehouse | Client Office: Washington, DC

Head of Marketing, Business Intelligence & Customer Experience

@ KONE | Istanbul Merkez

[Summer Internship 2024] CEG Data Analytics Intern

@ Agoda | Bangkok, Thailand

Data Analyst - KYC

@ Wise | London

Working Student Machine Learning Engineer

@ Celonis | Munich, Germany