DSC internal talk in March

Assoc. Prof. Hidetaka Kamigaito gave a lecture in March.

The details are as follows.

====================

Assoc. Prof. Hidetaka Kamigaito (Natural Language Processing Laboratory)

TITLE:
Recent Advances in Minimum Bayes Risk Decoding

ABSTRACT：
As represented by large language models (LLMs), generative AI models are fundamental tools in various fields. However, their generation results are sometimes unstable. To mitigate the issue, we can use Minimum Bayes Risk (MBR) decoding, which considers the consensus of generated candidates. In this presentation, I’ll introduce recent advances in MBR decoding, focusing primarily on its use in LLMs.