Weijia Shi

5

Papers

313

Total Citations

Papers (5)

RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation

In-Context Pretraining: Language Modeling Beyond Document Boundaries

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

PromptCap: Prompt-Guided Image Captioning for VQA with GPT-3

Fine-Grained Human Feedback Gives Better Rewards for Language Model Training