← Search

Tingting Dai

3 accepted papers

2025

SCE: Semantic Consistency Enhanced Reinforcement Learning for Multi-Hop Knowledge Graph Reasoning

EMNLP 2025

Multi-hop reasoning with reinforcement learning has proven effective in discovering inference paths in incomplete knowledge graphs. However, a major challenge remains: spurious paths (incorrect reasoning paths that accidentally lead to correct answers) often arise due to reward mechanisms that prior

Cited by 0SourcePDFScholar
2024

Spatial-Temporal Perceiving: Deciphering User Hierarchical Intent in Session-Based Recommendation

IJCAI 2024poster

Session-based recommendation (SBR) aims to predict the next-interacted item based on anonymous users' behavior sequences. The main challenge is how to recognize the user intent with limited interactions to achieve a more accurate inference of user behavior. Existing works usually regard several cons…