Xinran Zhao

Revela: Dense Retriever Learning via Language Modeling

Improving Attributed Long-form Question Answering with Intent Awareness

RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems

Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters

Pivot-ICL: Adaptive Exemplar Selection for In-Context Learning

Improving Large Language Model Planning with Action Sequence Similarity