Mechanistic Interpretability of Animacy Effects on Structure Choice in GPT-2 - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Yue Li, Yan Cong, Elaine J. Francis. Mechanistic Interpretability of Animacy Effects on Structure Choice in GPT-2. In Claire Bonial, Yevgeni Berzak, editors, Proceedings of the 30th Conference on Computational Natural Language Learning, CoNLL 2026, San Diego, California, USA, July 3-4, 2026. pages 626-640, Association for Computational Linguistics, 2026. [doi]

This author has not been identified. Look up 'Yue Li' in GoogleThis author has not been identified. Look up 'Yan Cong' in GoogleThis author has not been identified. Look up 'Elaine J. Francis' in Google

runs on WebDSL