NLP

Adaptive Decoding via Latent Preference Optimization

November 19, 2024

Abstract

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.

Download the Paper

AUTHORS

Written by

Shehzaad Dhuliawala

Ilia Kulikov

Ping Yu

Asli Celikyilmaz

Jason Weston

Sainbayar Sukhbaatar

Jack Lanchantin

Publisher

arXiv

Research Topics

Natural Language Processing (NLP)

Related Publications

March 24, 2026

NLP

OPEN SOURCE

HyperAgents

Jenny Zhang, Bingchen Zhao, Winnie Yang, Jakob Foerster, Sam Devlin, Tatiana Shavrina

March 24, 2026

Read the Paper

March 17, 2026

RESEARCH

NLP

Omnilingual MT: Machine Translation for 1,600 Languages

Omnilingual MT Team, Belen Alastruey, Niyati Bafna, Andrea Caciolai, Kevin Heffernan, Artyom Kozhevnikov, Christophe Ropers, Eduardo Sánchez, Charles-Eric Saint-James, Ioannis Tsiamas, Chierh CHENG, Joe Chuang, Paul-Ambroise Duquenne, Mark Duppenthaler, Nate Ekberg, Cynthia Gao, Pere Lluís Huguet Cabot, João Maria Janeiro, Jean Maillard, Gabriel Mejia Gonzalez, Holger Schwenk, Edan Toledo, Arina Turkatenko, Albert Ventayol-Boada, Rashel Moritz, Alexandre Mourachko, Surya Parimi, Mary Williamson, Shireen Yates, David Dale, Marta R. Costa-jussa

March 17, 2026

Read the Paper

March 17, 2026

RESEARCH

SPEECH & AUDIO

Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech

Omnilingual SONAR Team, João Maria Janeiro, Pere Lluís Huguet Cabot, Ioannis Tsiamas, Yen Meng, Vivek Iyer, Guillem Ramirez, Loic Barrault, Belen Alastruey, Yu-An Chung, Marta R. Costa-jussa, David Dale, Kevin Heffernan, Jaehyeong Jo, Artyom Kozhevnikov, Alexandre Mourachko, Christophe Ropers, Holger Schwenk, Paul-Ambroise Duquenne