Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Decoder-based Sense Knowledge Distillation
Qitong Wang, Mohammed J. Zaki, Georgios Kollias +1
Large language models (LLMs) learn contextual embeddings that capture rich semantic information, yet they often overlook structured lexical knowledge such as word senses and relati…
cs.CL2025
Multi-Sense Embeddings for Language Models and Knowledge Distillation
Qitong Wang, Mohammed J. Zaki, Georgios Kollias +1
Transformer-based large language models (LLMs) rely on contextual embeddings which generate different (continuous) representations for the same token depending on its surrounding c…