Skip to main content

🏢 College of Computer Science and Technology, Jilin University

Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss
·1724 words·9 mins· loading · loading
Semi-Supervised Learning 🏢 College of Computer Science and Technology, Jilin University
S2ML2-BBAM: A new semi-supervised multi-label learning method that balances feature angle distributions to improve accuracy and fairness.
Instance-adaptive Zero-shot Chain-of-Thought Prompting
·2222 words·11 mins· loading · loading
Natural Language Processing Large Language Models 🏢 College of Computer Science and Technology, Jilin University
Instance-adaptive prompting significantly improves zero-shot Chain-of-Thought reasoning in LLMs by dynamically selecting prompts tailored to each instance, leading to consistent performance gains acro…