Choo, J., Lee, J., Kim, J., Song, Y., Hong, S. K., & Kwon, Y. (2026). TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models.
Style de citation Chicago (17e éd.)Choo, Jinho, JunSeung Lee, Jimyeong Kim, Yeeho Song, S. K. Hong, et Yeong-Dae Kwon. TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models. 2026.
Style de citation MLA (9e éd.)Choo, Jinho, et al. TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models. 2026.
Attention : ces citations peuvent ne pas être correctes à 100%.