2 citations · 5 across the 9 of their papers we have counts for
4 papers · 1 filter
Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding
Yupeng Qi, Ziyu Lyu, Lixin Cui +2
Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem. However, existing methods for mitigating over-refu…
MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework
Yupeng Qi, Ziyu Lyu, Min Yang +3
As large language models (LLMs) are increasingly applied across various domains, enhancing safety while maintaining the helpfulness of LLMs has become a critical challenge. Recent…
Writing Style Aware Document-level Event Extraction
Zhuo Xu, Yue Wang, Lu Bai +1
Event extraction, the technology that aims to automatically get the structural information from documents, has attracted more and more attention in many fields. Most existing works…
Cross-Supervised Joint-Event-Extraction with Heterogeneous Information Networks
Yue Wang, Zhuo Xu, Lu Bai +5
Joint-event-extraction, which extracts structural information (i.e., entities or triggers of events) from unstructured real-world corpora, has attracted more and more research atte…