Jiawei Han

5 papers UIUC

• DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
• FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models
• Hybrid Latent Reasoning via Reinforcement Learning
• RAST: Reasoning Activation in LLMs via Small-model Transfer
• The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning