Ruifeng Xu

10

Papers

61

Total Citations

Papers (10)

CPPO: Continual Learning for Reinforcement Learning with Human Feedback

Training on the Benchmark Is Not All You Need

Enhancing Multi-Label Classification via Dynamic Label-Order Learning

Correcting Large Language Model Behavior via Influence Function

Centrality-guided Pre-training for Graph

A New Formula for Sticker Retrieval: Reply with Stickers in Multi-Modal and Multi-Session Conversation

Counterfactual-Enhanced Information Bottleneck for Aspect-Based Sentiment Analysis

BeyondGender: A Multifaceted Bilingual Dataset for Practical Sexism Detection

Adaptive Graph Learning for Multimodal Conversational Emotion Detection

Empowering Self-Learning of LLMs: Inner Knowledge Explicitation as a Catalyst