Fei Wang

Unraveling Indirect In-Context Learning Using Influence Functions

Unbiased Visual Reasoning with Controlled Visual Inputs

LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions

BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge

Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models

Aligning to Constraints for Data-Efficient Language Model Customization

MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding

Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models