Unified identity authentication method and system based on API gateway von ZHANG YINSHENG, BI LINGRUI, YUAN YE, GAO XIN

Volltext bestellen

Cloud rendering method and device, equipment and medium von MA TENG, LI XU, CHEN ZONGJUAN, BI LINGRUI, HE SHAOQING, TIAN YANG, LI DANDAN, CHENG XU, ZHANG CONGCONG, CAI JIANJUN

Volltext bestellen

SLANG: New Concept Comprehension of Large Language Models von Mei, Lingrui, Liu, Shenghua, Wang, Yiwei, Bi, Baolong, Cheng, Xueqi

Volltext bestellen

LPNL: Scalable Link Prediction with Large Language Models von Bi, Baolong, Liu, Shenghua, Wang, Yiwei, Mei, Lingrui, Cheng, Xueqi

Volltext bestellen

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router von Mei, Lingrui, Liu, Shenghua, Wang, Yiwei, Bi, Baolong, Yuan, Ruibin, Cheng, Xueqi

Volltext bestellen

StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models von Bi, Baolong, Liu, Shenghua, Wang, Yiwei, Mei, Lingrui, Gao, Hongcheng, Fang, Junfeng, Cheng, Xueqi

Volltext bestellen

Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities von Bi, Baolong, Liu, Shenghua, Wang, Yiwei, Mei, Lingrui, Gao, Hongcheng, Xu, Yilong, Cheng, Xueqi

Volltext bestellen

"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak von Mei, Lingrui, Liu, Shenghua, Wang, Yiwei, Bi, Baolong, Mao, Jiayi, Cheng, Xueqi

Volltext bestellen

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts von Bi, Baolong, Liu, Shenghua, Mei, Lingrui, Wang, Yiwei, Ji, Pengliang, Cheng, Xueqi

Volltext bestellen

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness von Bi, Baolong, Liu, Shenghua, Wang, Yiwei, Mei, Lingrui, Fang, Junfeng, Gao, Hongcheng, Ni, Shiyu, Cheng, Xueqi

Volltext bestellen

Can Graph Descriptive Order Affect Solving Graph Problems with LLMs? von Ge, Yuyao, Liu, Shenghua, Bi, Baolong, Wang, Yiwei, Mei, Lingrui, Feng, Wenjie, Chen, Lizhe, Cheng, Xueqi

Volltext bestellen

Context-DPO: Aligning Language Models for Context-Faithfulness von Bi, Baolong, Huang, Shaohan, Wang, Yiwei, Yang, Tianchi, Zhang, Zihan, Huang, Haizhen, Mei, Lingrui, Fang, Junfeng, Li, Zehao, Wei, Furu, Deng, Weiwei, Sun, Feng, Zhang, Qi, Liu, Shenghua

Volltext bestellen

SLANG: New Concept Comprehension of Large Language Models von Lingrui Mei, Liu, Shenghua, Wang, Yiwei, Bi, Baolong, Cheng, Xueqi

Volltext

LPNL: Scalable Link Prediction with Large Language Models von Bi, Baolong, Liu, Shenghua, Wang, Yiwei, Lingrui Mei, Cheng, Xueqi

Volltext

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness von Bi, Baolong, Liu, Shenghua, Wang, Yiwei, Lingrui Mei, Fang, Junfeng, Gao, Hongcheng, Ni, Shiyu, Cheng, Xueqi

Volltext

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router von Lingrui Mei, Liu, Shenghua, Wang, Yiwei, Bi, Baolong, Yuan, Ruibin, Cheng, Xueqi

Volltext

StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models von Bi, Baolong, Liu, Shenghua, Wang, Yiwei, Lingrui Mei, Gao, Hongcheng, Fang, Junfeng, Cheng, Xueqi

Volltext

Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities von Bi, Baolong, Liu, Shenghua, Wang, Yiwei, Lingrui Mei, Gao, Hongcheng, Xu, Yilong, Cheng, Xueqi

Volltext

"Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak von Lingrui Mei, Liu, Shenghua, Wang, Yiwei, Bi, Baolong, Mao, Jiayi, Cheng, Xueqi

Volltext

Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts von Bi, Baolong, Liu, Shenghua, Lingrui Mei, Wang, Yiwei, Ji, Pengliang, Cheng, Xueqi

Volltext