Hongyu Lin

6

Papers

614

Total Citations

Papers (6)

Benchmarking Large Language Models in Retrieval-Augmented Generation

Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-Based Retrofitting

StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model

ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers

DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation