Papers by Katsumi Ibaraki

1 papers
Analyzing Occupational Distribution Representation in Japanese Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Recent advances in large language models have enabled users to generate fluent and seemingly convincing text, but they have uneven performance in different languages, which is associated with undesirable societal biases toward marginalized populations.
Approach: They develop three Japanese language prompts to probe LLMs’ understanding of Japanese names and their association between gender and occupations.
Outcome: The proposed models can associate Japanese names with correct gendered occupations when using constrained decoding, but with sampling or greedy decoding they prefer a small set of stereotypically genderes.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations