most citedLightKG: Efficient Knowledge-Aware Recommendations with Simplified GNN Architecture

9 citations · 9 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2025

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models

Kexin Chen, Dongxia Wang, Yi Liu +2

Despite the widespread use of Transformer-based text embedding models in NLP tasks, surprising 'sticky tokens' can undermine the reliability of embeddings. These tokens, when repea…