 Dynamic Fisher-weighted Model Merging via Bayesian OptimizationNorth American Chapter of the Association for Computational Linguistics (NAACL), 2025 |
 Weak-to-Strong Generalization Through the Data-Centric LensInternational Conference on Learning Representations (ICLR), 2024 |
 FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research Jiajie Jin Yutao Zhu Xinyu Yang Chenghao Zhang Zhicheng Dou Chenghao Zhang Tong Zhao Zhao Yang Zhicheng Dou Ji-Rong Wen |
 Localizing Task Information for Improved Model Merging and CompressionInternational Conference on Machine Learning (ICML), 2024 |
 Crystal: Introspective Reasoners Reinforced with Self-FeedbackConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Learning Deductive Reasoning from Synthetic Corpus based on Formal LogicInternational Conference on Machine Learning (ICML), 2023 |
 KoRC: Knowledge oriented Reading Comprehension Benchmark for Deep Text
UnderstandingAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 Text Alignment Is An Efficient Unified Model for Massive NLP TasksNeural Information Processing Systems (NeurIPS), 2023 |
 TIES-Merging: Resolving Interference When Merging ModelsNeural Information Processing Systems (NeurIPS), 2023 |
 Language Models with RationalityConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Teaching Probabilistic Logical Reasoning to TransformersFindings (Findings), 2023 |
 Pre-Training to Learn in ContextAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 Vera: A General-Purpose Plausibility Estimation Model for Commonsense
StatementsConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Answering Questions by Meta-Reasoning over Multiple Chains of ThoughtConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language
ModelsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language
ModelsInternational Conference on Learning Representations (ICLR), 2022 |
 Entailer: Answering Questions with Faithful and Truthful Chains of
ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task
GeneralizationConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 "John is 50 years old, can his son be 65?" Evaluating NLP Models'
Understanding of FeasibilityConference of the European Chapter of the Association for Computational Linguistics (EACL), 2022 |
 Task Compass: Scaling Multi-task Pre-training with Task PrefixConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 REV: Information-Theoretic Evaluation of Free-Text RationalesAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Rainier: Reinforced Knowledge Introspector for Commonsense Question
AnsweringConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Guess the Instruction! Flipped Learning Makes Language Models Stronger
Zero-Shot LearnersInternational Conference on Learning Representations (ICLR), 2022 |
 Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple
TasksAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Few-shot Adaptation Works with UnpredicTable DataAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Eliciting and Understanding Cross-Task Skills with Task-Level
Mixture-of-ExpertsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Investigating the Benefits of Free-Form RationalesConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Interpretable Proof Generation via Iterative Backward ReasoningNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Towards Teachable Reasoning Systems: Using a Dynamic Memory of User
Feedback for Continual System ImprovementConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 UKP-SQUARE: An Online Platform for Question Answering ResearchAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 FaiRR: Faithful and Robust Deductive Reasoning over Natural LanguageAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
