notesum.ai

Published at November 13

Code-mixed LLM: Improve Large Language Models' Capability to Handle Code-Mixing through Reinforcement Learning from AI Feedback

cs.CL

cs.AI

cs.LG

Released Date: November 13, 2024

Authors: Wenbo Zhang¹, Aditya Majumdar¹, Amulya Yadav¹

Aff.: ¹Pennsylvania State University

Arxiv: http://arxiv.org/abs/2411.09073v1

Model Name	BLEU
mT0-base	45.89
mBART50	65.90
M2M100	63.46
GPT-4	14.28