2 papers
cs.CL2026
Humans and transformer LMs: Abstraction drives language learning
Jasper Jian, Christopher D. Manning
Categorization is a core component of human linguistic competence. We investigate how a transformer-based language model (LM) learns linguistic categories by comparing its behaviou…
cs.CL2025
Mechanisms vs. Outcomes: Probing for Syntax Fails to Explain Performance on Targeted Syntactic Evaluations
Ananth Agarwal, Jasper Jian, Christopher D. Manning +1
Large Language Models (LLMs) exhibit a robust mastery of syntax when processing and generating text. While this suggests internalized understanding of hierarchical syntax and depen…