Multiple papers accepted to top venues: NeurIPS 2025, ICML 2025, ICLR 2025, ACL 2025 Findings, NAACL 2025 (3 papers), TMLR.
Organized workshops including BlackboxNLP @ EMNLP 2024 and The First Workshop on LLM Explainability for Reasoning and Planning @ COLM 2025.
Serving as Senior Area Chair for ACL 2025.
Delivered a tutorial on 'Explanation in the Era of Large Language Models' at NAACL 2024.
Authored several arXiv preprints, including 'Language Models are Symbolic Learners in Arithmetic', 'MiCEval', 'From Babbling to Fluency', and 'SPORTU'.
Invited to give numerous talks on LLM interpretability, control, medical applications, ethics, and cognitive modeling at universities and conferences.