Hiroaki Yamagiwa
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment
According to the abstract excerpt, Itai, Hirako and Yamagiwa extend the refusal-direction approach to three reasons a language model may decline to answer: unclear queries, limits of its knowledge, and conflict with human values. They report steering experiments in middle layers.