Yunchang Zhu

LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback

2022 · arXiv (Cornell University)

Pseudo-relevance feedback (PRF) has proven to be an effective query reformulation technique to improve retrieval accuracy. It aims to alleviate the mismatch of linguistic expressions between a query and its potential relevant documents. Existing PRF …

RLKD: Distilling LLMs' Reasoning via Reinforcement Learning

2025 · arXiv (Cornell University)

Distilling reasoning paths from teacher to student models via supervised fine-tuning (SFT) provides a shortcut for improving the reasoning ability of smaller Large Language Models (LLMs). However, the reasoning paths generated by teacher models often …