LLM Interpretability
Li, Y., Cong, Y., & Francis, E. Illuminating Human Language Production via Mechanistic Interpretability of LM Circuits: Animacy Effects on Sentence Structure Choice. Poster, HSP 2026, MIT.
Fang, S., Li, Y., & Cong, Y. Can LLMS Read Between the Scopes? A Cross-Linguistic Study of Quantifier-Negation Interpretations. LSA 2026, New Orleans, USA.
Fang, S., Li, Y., & Cong, Y. Understanding Quantifier Scope with Large Language Models: How Many Children Climbed Trees?. CogSci 2025, San Francisco, USA.
Li, Y., Cong, Y., & Francis, E. Beyond Binary Animacy: A Multi-Method Investigation of LMs’ Sensitivity inEnglish Object Relative Clause. CMCL 2025, Albuquerque, New Mexico, USA.
