54 citations · 90 across the 25 of their papers we have counts for
7 papers · 1 filter
Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?
Yuu Jinnai
Alignment of the language model with human preferences is a common approach to making a language model useful to end users. However, most alignment work is done in English, and hum…
Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts
Yuu Jinnai, Ukyo Honda
Preference optimization is a standard approach to fine-tuning large language models to align with human preferences. The quantity, diversity, and representativeness of the preferen…
Filtered Direct Preference Optimization
Tetsuro Morimura, Mitsuki Sakamoto, Yuu Jinnai +2
Reinforcement learning from human feedback (RLHF) plays a crucial role in aligning language models with human preferences. While the significance of dataset quality is generally re…
Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment
Yuu Jinnai, Tetsuro Morimura, Kaito Ariu +1
Best-of-N (BoN) sampling with a reward model has been shown to be an effective strategy for aligning Large Language Models (LLMs) to human preferences at the time of decoding. BoN…
On the True Distribution Approximation of Minimum Bayes-Risk Decoding
Atsumoto Ohashi, Ukyo Honda, Tetsuro Morimura +1
Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation. MBR decoding considers texts sampled from a model as pseudo-references and selects the t…
Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding
Yuu Jinnai, Ukyo Honda, Tetsuro Morimura +1
One of the most important challenges in text generation systems is to produce outputs that are not only correct but also diverse. Recently, Minimum Bayes-Risk (MBR) decoding has ga…
Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding
Yuu Jinnai, Kaito Ariu
Minimum Bayes-Risk (MBR) decoding is shown to be a powerful alternative to beam search decoding for a wide range of text generation tasks. However, MBR requires a huge amount of ti…