 Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of
Language ModelsInternational Conference on Learning Representations (ICLR), 2023 |
 Physics of Language Models: Part 3.1, Knowledge Storage and ExtractionInternational Conference on Machine Learning (ICML), 2023 |
 MAmmoTH: Building Math Generalist Models through Hybrid Instruction
TuningInternational Conference on Learning Representations (ICLR), 2023 |
 WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-InstructInternational Conference on Learning Representations (ICLR), 2023 |
 Self-Instruct: Aligning Language Models with Self-Generated InstructionsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Large Language Models Are Reasoning TeachersAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Scaling Instruction-Finetuned Language ModelsJournal of machine learning research (JMLR), 2022 |
 Solving Quantitative Reasoning Problems with Language ModelsNeural Information Processing Systems (NeurIPS), 2022 |
 Training language models to follow instructions with human feedbackNeural Information Processing Systems (NeurIPS), 2022 |
 AEDA: An Easier Data Augmentation Technique for Text ClassificationConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Attention is not not ExplanationConference on Empirical Methods in Natural Language Processing (EMNLP), 2019 |
 Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy
Lifting, the Rest Can Be PrunedAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Unsupervised Data Augmentation for Consistency TrainingNeural Information Processing Systems (NeurIPS), 2019 |
 Attention is not ExplanationNorth American Chapter of the Association for Computational Linguistics (NAACL), 2019 |
 mixup: Beyond Empirical Risk MinimizationInternational Conference on Learning Representations (ICLR), 2017 |
