 Enough Coin Flips Can Make LLMs Act BayesianAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 |
 Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?International Conference on Learning Representations (ICLR), 2025 |
 Out-of-distribution generalization via composition: a lens through induction heads in TransformersProceedings of the National Academy of Sciences of the United States of America (PNAS), 2024 |
 Racing Thoughts: Explaining Contextualization Errors in Large Language ModelsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2024 |
 In-Context Learning with Representations: Contextual Generalization of
Trained TransformersNeural Information Processing Systems (NeurIPS), 2024 |
 On Subjective Uncertainty Quantification and Calibration in Natural
Language GenerationInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 |
 What Do Language Models Learn in Context? The Structured Task HypothesisAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Can large language models explore in-context?Neural Information Processing Systems (NeurIPS), 2024 |
 Concept-aware Data Construction Improves In-context Learning of Language
ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Learning Universal PredictorsInternational Conference on Machine Learning (ICML), 2024 |
 Demystifying Chains, Trees, and Graphs of ThoughtsIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024 |
 In-Context Language Learning: Architectures and AlgorithmsInternational Conference on Machine Learning (ICML), 2024 |
 Universal Vulnerabilities in Large Language Models: Backdoor Attacks for
In-context LearningConference on Empirical Methods in Natural Language Processing (EMNLP), 2024 |
 How are Prompts Different in Terms of Sensitivity?North American Chapter of the Association for Computational Linguistics (NAACL), 2023 |
 Gen-Z: Generative Zero-Shot Text Classification with Contextualized
Label DescriptionsInternational Conference on Learning Representations (ICLR), 2023 |
 The Mystery of In-Context Learning: A Comprehensive Survey on
Interpretation and AnalysisConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 In-Context Learning Dynamics with Random Binary SequencesInternational Conference on Learning Representations (ICLR), 2023 |
 Function Vectors in Large Language ModelsInternational Conference on Learning Representations (ICLR), 2023 |
