 Using Large Language Models to Categorize Strategic Situations and Decipher Motivations Behind Human BehaviorsProceedings of the National Academy of Sciences of the United States of America (PNAS), 2025 |
 In-Context Learning (and Unlearning) of Length BiasesNorth American Chapter of the Association for Computational Linguistics (NAACL), 2025 |
 Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient DescentInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 |
 Calibrating Language Models with Adaptive Temperature ScalingConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 Think Twice Before Trusting: Self-Detection for Large Language Models
through Comprehensive Answer ReflectionConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 Understanding the Effects of Iterative Prompting on TruthfulnessInternational Conference on Machine Learning (ICML), 2024 |
