75 citations · 244 across the 21 of their papers we have counts for
21 papers
VARM-Bench: Benchmarking Verifiable Structured Reasoning in Chinese Abusive Speech Moderation
Mingyu Yuan, Shengtao Wen, Lingbing Guo +2
The widespread circulation of abusive online content has increased the need for reliable moderation of Chinese social-media text. Existing Chinese benchmarks support label classifi…
SkillNet: Create, Evaluate, and Connect AI Skills
Yuan Liang, Ruobin Zhong, Haoming Xu +47
Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Wi…
BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models
Gaurav Srivastava, Aafiya Hussain, Zhenyu Bi +5
Evaluating language models fairly is increasingly difficult as static benchmarks risk contamination by training data, obscuring whether models truly reason or recall. We introduce…
Spatial Knowledge Graph-Guided Multimodal Synthesis
Yida Xue, Zhen Bi, Jinnan Yang +5
Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced their capabilities; however, their spatial perception abilities remain a notable limitation.…
EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models
Yixin Ou, Ningyu Zhang, Honghao Gui +9
In recent years, instruction tuning has gained increasing attention and emerged as a crucial technique to enhance the capabilities of Large Language Models (LLMs). To construct hig…
OceanGPT: A Large Language Model for Ocean Science Tasks
Zhen Bi, Ningyu Zhang, Yida Xue +4
Ocean science, which delves into the oceans that are reservoirs of life and biodiversity, is of great significance given that oceans cover over 70% of our planet's surface. Recentl…
When Do Program-of-Thoughts Work for Reasoning?
Zhen Bi, Ningyu Zhang, Yinuo Jiang +3
In the realm of embodied artificial intelligence, the reasoning capabilities of Large Language Models (LLMs) play a pivotal role. Although there are effective methods like program-…
CodeKGC: Code Language Model for Generative Knowledge Graph Construction
Zhen Bi, Jing Chen, Yinuo Jiang +4
Current generative knowledge graph construction approaches usually fail to capture structural knowledge by simply flattening natural language into serialized texts or a specificati…
Tele-Knowledge Pre-training for Fault Analysis
Zhuo Chen, Wen Zhang, Yufeng Huang +14
In this work, we share our experience on tele-knowledge pre-training for fault analysis, a crucial task in telecommunication applications that requires a wide range of knowledge no…
Multi-modal Protein Knowledge Graph Construction and Applications
Siyuan Cheng, Xiaozhuan Liang, Zhen Bi +2
Existing data-centric methods for protein science generally cannot sufficiently capture and leverage biology knowledge, which may be crucial for many protein tasks. To facilitate r…
Relphormer: Relational Graph Transformer for Knowledge Graph Representations
Zhen Bi, Siyuan Cheng, Jing Chen +3
Transformers have achieved remarkable performance in widespread fields, including natural language processing, computer vision and graph mining. However, vanilla Transformer archit…
Contrastive Demonstration Tuning for Pre-trained Language Models
Xiaozhuan Liang, Ningyu Zhang, Siyuan Cheng +3
Pretrained language models can be effectively stimulated by textual prompts or demonstrations, especially in low-data scenarios. Recent works have focused on automatically searchin…
OntoProtein: Protein Pretraining With Gene Ontology Embedding
Ningyu Zhang, Zhen Bi, Xiaozhuan Liang +6
Self-supervised protein language models have proved their effectiveness in learning the proteins representations. With the increasing computational power, current protein language…
Improving Knowledge Graph Representation Learning by Structure Contextual Pre-training
Ganqiang Ye, Wen Zhang, Zhen Bi +3
Representation learning models for Knowledge Graphs (KG) have proven to be effective in encoding structural information and performing reasoning over KGs. In this paper, we propose…
Learning to Ask for Data-Efficient Event Argument Extraction
Hongbin Ye, Ningyu Zhang, Zhen Bi +5
Event argument extraction (EAE) is an important task for information extraction to discover specific argument roles. In this study, we cast EAE as a question-based cloze task and e…
Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners
Ningyu Zhang, Luoqiu Li, Xiang Chen +5
Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their eff…
CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark
Ningyu Zhang, Mosha Chen, Zhen Bi +20
Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually changing medical practice. With the development of biomedical langua…
Interventional Aspect-Based Sentiment Analysis
Zhen Bi, Ningyu Zhang, Ganqiang Ye +3
Recent neural-based aspect-based sentiment analysis approaches, though achieving promising improvement on benchmark datasets, have reported suffering from poor robustness when enco…
Disentangled Contrastive Learning for Learning Robust Textual Representations
Xiang Chen, Xin Xie, Zhen Bi +4
Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-o…
Text-guided Legal Knowledge Graph Reasoning
Luoqiu Li, Zhen Bi, Hongbin Ye +3
Recent years have witnessed the prosperity of legal artificial intelligence with the development of technologies. In this paper, we propose a novel legal application of legal provi…
On Robustness and Bias Analysis of BERT-based Relation Extraction
Luoqiu Li, Xiang Chen, Hongbin Ye +4
Fine-tuning pre-trained models have achieved impressive performance on standard natural language processing benchmarks. However, the resultant model generalizability remains poorly…