Wataru Hirota
2 papers · Latest:
Natural Language Processing
Why Expert Alignment Is Hard: Evidence from Subjective Evaluation
This paper reveals why aligning LLMs with expert judgment in subjective tasks is difficult, highlighting heterogeneity, tacit knowledge, and dimension dependency.
2605.04972
Natural Language ProcessingAggregate vs. Personalized Judges in Business Idea Evaluation: Evidence from Expert Disagreement
Personalized judges align better with experts than aggregate judges in evaluating business ideas, using a new dataset, PBIG-DATA.
2604.22517
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.