Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence

Junru Lu | Jiazheng Li | Siyu An | Meng Zhao | Yulan He | Di Yin | Xing Sun |

Paper Details:

Month: November
Year: 2024
Location: Miami, Florida, USA
Venue: EMNLP |

Citations

URL

No Citations Yet

Field Of Study