Zhiqiang Zhan

All That Glitters is Not Gold: Improving Robust Retrieval-Augmented Language Models with Fact-Centric Preference Alignment

Retrieval-augmented language model (RALM) relies on retrieved external knowledge to generate responses, resulting in vulnerability in the face of retrieval results with noisy documents. Previous works integrate additional filters or finetune Large Language Models (LLMs) to learn adaptive retrieval t…