最新

• CS-Bench:A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery
• BootTOD:Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses
• DivTOD:Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations
• PreAct:Predicting Future in ReAct Enhances Agent's Planning Ability
• A multi-task semantic decomposition framework with task-specific pre-training for few-shot ner
• A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Named Entity Recognition
• Revisit Out-Of-Vocabulary Problem For Slot Filling: A Unified Contrastive Framework With Multi-Level Data Augmentations
• Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog Systems