November 19, 2024
During language model decoding, it is known that using higher temperature sampling gives more creative responses, while lower temperatures are more factually accurate. However, such models are commonly applied to general instruction following, which involves both creative and fact seeking tasks, using a single fixed temperature across all examples and tokens. In this work, we introduce Adaptive Decoding, a layer added to the model to select the sampling temperature dynamically at inference time, at either the token or example level, in order to optimize performance. To learn its parameters we introduce Latent Preference Optimization (LPO) a general approach to train discrete latent variables such as choices of temperature. Our method outperforms all fixed decoding temperatures across a range of tasks that require different temperatures, including UltraFeedback, Creative Story Writing, and GSM8K.
Written by
Shehzaad Dhuliawala
Ilia Kulikov
Ping Yu
Asli Celikyilmaz
Jack Lanchantin
Publisher
arXiv
Research Topics
July 02, 2025
Joongwon (Daniel) Kim, Anirudh Goyal, Liang Tan, Hannaneh Hajishirzi, Srini Iyer, Tianlu Wang
July 02, 2025
May 14, 2025
Linnea Evanson, Christine Bulteau, Mathilde Chipaux, Georg Dorfmüller, Sarah Ferrand-Sorbets, Emmanuel Raffo, Sarah Rosenberg, Pierre Bourdillon, Jean Remi King
May 14, 2025
April 25, 2025
Rulin Shao, Qiao Rui, Varsha Kishore, Niklas Muennighoff, Victoria Lin, Daniela Rus, Bryan Kian Hsiang Low, Sewon Min, Scott Yih, Pang Wei Koh, Luke Zettlemoyer
April 25, 2025
April 17, 2025
Ansong Ni, Ruta Desai, Yang Li, Xinjie Lei, Dong Wang, Ramya Raghavendra, Gargi Ghosh, Daniel Li (FAIR), Asli Celikyilmaz
April 17, 2025
Our approach
Latest news
Foundational models