Jia, Robin
13 publications
ICLR
2026
Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions
ICLR
2026
Function Induction and Task Generalization: An Interpretability Study with Off-by-One Addition
NeurIPSW
2024
Language Models and Symbolic Planners Can Infer Action Semantics Through Environment Feedback
NeurIPS
2024
Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression
NeurIPSW
2023
Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models