notesum.ai

Published at October 20

Mitigating Forgetting in LLM Supervised Fine-Tuning and Preference Learning

cs.CL
cs.AI
cs.IR

Released Date: October 20, 2024

Authors: Heshan Fernando1, Han Shen1, Parikshit Ram2, Yi Zhou2, Horst Samulowitz2, Nathalie Baracaldo2, Tianyi Chen1

Aff.: 1Rensselaer Polytechnic Institute; 2IBM Research

Arxiv: https://arxiv.org/abs/2410.15483v1