2 papers
cs.CL2026
REZE: Representation Regularization for Domain-adaptive Text Embedding Pre-finetuning
Seungmin Lee, Jeonghwan Lee, Hyunkuk Lim +2
Recent text embedding models are often adapted to specialized domains via contrastive pre-finetuning (PFT) on a naive collection of scattered, heterogeneous tasks. However, this ap…
cs.CL2024
Efficient Terminology Integration for LLM-based Translation in Specialized Domains
Sejoon Kim, Mingi Sung, Jeonghwan Lee +2
Traditional machine translation methods typically involve training models directly on large parallel corpora, with limited emphasis on specialized terminology. However, In speciali…