1 citations · 1 across the 5 of their papers we have counts for
6 papers
RLKD: Distilling LLMs' Reasoning via Reinforcement Learning
Shicheng Xu, Liang Pang, Yunchang Zhu +6
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…
Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
Shicheng Xu, Liang Pang, Yunchang Zhu +2
Vision-language alignment in Large Vision-Language Models (LVLMs) successfully enables LLMs to understand visual input. However, we find that existing vision-language alignment met…
Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding
Yunchang Zhu, Liang Pang, Kangxi Wu +3
Current natural language understanding (NLU) models have been continuously scaling up, both in terms of model size and input context, introducing more hidden and input neurons. Whi…
LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback
Yunchang Zhu, Liang Pang, Yanyan Lan +2
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 expressio…
Adaptive Information Seeking for Open-Domain Question Answering
Yunchang Zhu, Liang Pang, Yanyan Lan +2
Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus. Recently, iterative approaches have been proven to b…
L2R2: Leveraging Ranking for Abductive Reasoning
Yunchang Zhu, Liang Pang, Yanyan Lan +1
The abductive natural language inference task (NLI) is proposed to evaluate the abductive reasoning ability of a learning system. In the NLI task, two observations are given…