Back to papers
April 29, 2026cs.CLcs.AIcs.LG

TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models

Jinho Choo, JunSeung Lee, Jimyeong Kim, Yeeho Song, S. K. Hong, Yeong-Dae Kwon
Read on arXivDownload PDF
Categories

cs.CL, cs.AI, cs.LG