 Sequence-level Large Language Model Training with Contrastive Preference OptimizationNorth American Chapter of the Association for Computational Linguistics (NAACL), 2025 |
 Beyond MLE: Convex Learning for Text GenerationNeural Information Processing Systems (NeurIPS), 2023 |
 Building Persona Consistent Dialogue Agents with Offline Reinforcement
LearningConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 EMO: Earth Mover Distance Optimization for Auto-Regressive Language
ModelingInternational Conference on Learning Representations (ICLR), 2023 |
 Language Model Decoding as Direct Metrics OptimizationInternational Conference on Learning Representations (ICLR), 2023 |
 ESRL: Efficient Sampling-based Reinforcement Learning for Sequence
GenerationAAAI Conference on Artificial Intelligence (AAAI), 2023 |
 On the Effectiveness of Offline RL for Dialogue Response GenerationInternational Conference on Machine Learning (ICML), 2023 |
 On the Efficacy of Sampling AdaptersAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 Semi-Offline Reinforcement Learning for Optimized Text GenerationInternational Conference on Machine Learning (ICML), 2023 |
 MiniLLM: Knowledge Distillation of Large Language ModelsInternational Conference on Learning Representations (ICLR), 2023 |
 Preference-grounded Token-level Guidance for Language Model Fine-tuningNeural Information Processing Systems (NeurIPS), 2023 |
 Zero-shot Visual Question Answering with Language Model FeedbackAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 Leftover Lunch: Advantage-based Offline Reinforcement Learning for
Language ModelsInternational Conference on Learning Representations (ICLR), 2023 |
 On Learning to Summarize with Large Language Models as ReferencesNorth American Chapter of the Association for Computational Linguistics (NAACL), 2023 |
 Self-Edit: Fault-Aware Code Editor for Code GenerationAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 |
 GEMINI: Controlling the Sentence-level Writing Style for Abstractive
Text SummarizationConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 SPEC: Summary Preference Decomposition for Low-Resource Abstractive
SummarizationIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2023 |
 Tailoring Language Generation Models under Total Variation DistanceInternational Conference on Learning Representations (ICLR), 2023 |
 Learning with Rejection for Abstractive Text SummarizationConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Weakly-Supervised Questions for Zero-Shot Relation ExtractionConference of the European Chapter of the Association for Computational Linguistics (EACL), 2023 |
 Revisiting the Gold Standard: Grounding Summarization Evaluation with
Robust Human EvaluationAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 KRLS: Improving End-to-End Response Generation in Task Oriented Dialog
with Reinforced Keywords LearningConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 GoSum: Extractive Summarization of Long Documents by Reinforcement
Learning and Graph Organized discourse stateKnowledge and Information Systems (KAIS), 2022 |
 Reward Gaming in Conditional Text GenerationAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Teacher Forcing Recovers Reward Functions for Text GenerationNeural Information Processing Systems (NeurIPS), 2022 |
 Text Summarization with Oracle ExpectationInternational Conference on Learning Representations (ICLR), 2022 |
 Coarse-to-Fine Vision-Language Pre-training with Fusion in the BackboneNeural Information Processing Systems (NeurIPS), 2022 |
 Offline RL for Natural Language Generation with Implicit Language Q
LearningInternational Conference on Learning Representations (ICLR), 2022 |
 Knowledge Infused DecodingInternational Conference on Learning Representations (ICLR), 2022 |
 BRIO: Bringing Order to Abstractive SummarizationAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 AgreeSum: Agreement-Oriented Multi-Document SummarizationFindings (Findings), 2021 |
