Posts by Collection

portfolio

publications

Benchmarking and Improving LLM Robustness for Personalized Generation

Published in Findings of the Empirical Methods in Natural Language Processing (EMNLP), 2025

This paper highlights the issues associated with the current evaluation approaches in personalization that focus solely on preference alignment and adovate for a multidemnsional evaluation approach instead

Recommended citation: Chimaobi Okite, Naihao Deng, Kiran Bodipati, Huaidian Hou, Joyce Chai, Rada Mihalcea. (2025). "Benchmarking and Improving LLM Robustness for Personalized Generation" In Findings of the Empirical Methods in Natural Language Processing .
Download Paper

talks

teaching