北京通用人工智能研究院BIGAI

科研成果

Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels

Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling

LooGLE: Can Long-Context Language Models Understand Long Contexts?

Semi-automatic Data Enhancement for Document-Level Relation Extraction with Distant Supervision from Large Language Models

DiploMAT: A Dialogue Dataset for Situated PragMATic Reasoning

Modeling Instance Interactions for Joint Information Extraction with Neural High-Order Conditional Random Field