Rakshit, Supantho, Jennifer Hu, Kyle Mahowald, and Adele E Goldberg. 2026. “A Suite of LMs Comprehend Puzzle Statements As Well or Better Than Humans”. Open Mind 10: 431-40.

Goldberg, Rakshit and AE. 2025. “Meaning-Infused Grammar: Gradient Acceptability Shapes the Geometric Representations of Constructions in LLMs”. 16th International Conference on Computational Semantics. Duesseldorf, Germany.