Search Results for author: Kaiyang Wan

Found 6 papers, 5 papers with code

Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs

no code implementations21 May 2025 Lang Gao, Kaiyang Wan, Wei Liu, Chenxi Wang, Zirui Song, Zixiang Xu, Yanbo Wang, Veselin Stoyanov, Xiuying Chen

We focus on a common form of bias: when two reference concepts in the model's concept space, such as sentiment polarities (e. g., "positive" and "negative"), are asymmetrically correlated with a third, target concept, such as a reviewing aspect, the model exhibits unintended bias.

A Cognitive Writing Perspective for Constrained Long-Form Text Generation

1 code implementation18 Feb 2025 Kaiyang Wan, Honglin Mu, Rui Hao, Haoran Luo, Tianle Gu, Xiuying Chen

Like humans, Large Language Models (LLMs) struggle to generate high-quality long-form text that adheres to strict requirements in a single pass.

Form Text Generation

HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level

1 code implementation ACL 2023 Haoran Luo, Haihong E, Yuhao Yang, Yikai Guo, Mingzhi Sun, Tianyu Yao, Zichen Tang, Kaiyang Wan, Meina Song, Wei Lin

The global-level attention can model the graphical structure of HKG using hypergraph dual-attention layers, while the local-level attention can learn the sequential structure inside H-Facts via heterogeneous self-attention layers.

Attribute Knowledge Graphs +2

DHGE: Dual-View Hyper-Relational Knowledge Graph Embedding for Link Prediction and Entity Typing

1 code implementation AAAI 2023 Haoran Luo, Haihong E, Ling Tan, Gengxian Zhou, Tianyu Yao, Kaiyang Wan

To overcome this limitation, we propose a dual-view hyper-relational KG structure (DH-KG) that contains a hyper-relational instance view for entities and a hyper-relational ontology view for concepts that are abstracted hierarchically from the entities.

Attribute Entity Typing on DH-KGs +4

Cannot find the paper you are looking for? You can Submit a new open access paper.