9 papers
Understanding the Dynamics of Demonstration Conflict in In-Context Learning
Difan Jiao, Di Wang, Lijie Hu
In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting…
Controllable Concept Bottleneck Models
Hongbin Lin, Chenyang Ren, Juangui Xu +7
Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most prev…
Backdooring CLIP through Concept Confusion
Lijie Hu, Junchi Liao, Weimin Lyu +5
Backdoor attacks pose a serious threat to deep learning models by allowing adversaries to implant hidden behaviors that remain dormant on clean inputs but are maliciously triggered…
Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment
Huanyi Xie, Lijie Hu, Lu Yu +6
In the realm of Text-attributed Graphs (TAGs), traditional graph neural networks (GNNs) often fall short due to the complex textual information associated with each node. Recent me…
Semi-supervised Concept Bottleneck Models
Lijie Hu, Tianhao Huang, Huanyi Xie +6
Concept Bottleneck Models (CBMs) have garnered increasing attention due to their ability to provide concept-based explanations for black-box deep learning models while achieving hi…
Exploring the Personality Traits of LLMs through Latent Features Steering
Shu Yang, Shenzhe Zhu, Liang Liu +3
Large language models (LLMs) have significantly advanced dialogue systems and role-playing agents through their ability to generate human-like text. While prior studies have shown…