Research
2025
-
-
AgentOrca: A Dual-System Framework to Evaluate Language Agents on Operational Routine and Constraint AdherenceIn Findings of the Association for Computational Linguistics: ACL 2025, 2025 -
Generalization v.s. Memorization: Tracing Language Models’ Capabilities Back to Pretraining DataIn The Thirteenth International Conference on Learning Representations, 2025
2024
-
Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement LearningIn Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024