Saved in:
Bibliographic Details
Main Authors: Liu, Yang, Yang, Jiaye, Li, Weikang, Liang, Jiahui, Li, Yang, Yan, Lingyong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.14060
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912906191306752
author Liu, Yang
Yang, Jiaye
Li, Weikang
Liang, Jiahui
Li, Yang
Yan, Lingyong
author_facet Liu, Yang
Yang, Jiaye
Li, Weikang
Liang, Jiahui
Li, Yang
Yan, Lingyong
contents We introduce LM-Lexicon, an innovative definition modeling approach that incorporates data clustering, semantic expert learning, and model merging using a sparse mixture-of-experts architecture. By decomposing the definition modeling task into specialized semantic domains, where small language models are trained as domain experts, LM-Lexicon achieves substantial improvements (+7% BLEU score compared with the prior state-of-the-art model) over existing methods on five widely used benchmarks. Empirically, we demonstrate that 1) the clustering strategy enables fine-grained expert specialization with nearly 10% improvement in definition quality; 2) the semantic-aware domain-level routing mechanism achieves higher expert efficacy (+1%) than conventional token-level routing; and 3) further performance gains can be obtained through test-time compute and semantic expert scaling. Our work advances definition modeling while providing insights into the development of efficient language models for semantic-intensive applications.
format Preprint
id arxiv_https___arxiv_org_abs_2602_14060
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts
Liu, Yang
Yang, Jiaye
Li, Weikang
Liang, Jiahui
Li, Yang
Yan, Lingyong
Computation and Language
We introduce LM-Lexicon, an innovative definition modeling approach that incorporates data clustering, semantic expert learning, and model merging using a sparse mixture-of-experts architecture. By decomposing the definition modeling task into specialized semantic domains, where small language models are trained as domain experts, LM-Lexicon achieves substantial improvements (+7% BLEU score compared with the prior state-of-the-art model) over existing methods on five widely used benchmarks. Empirically, we demonstrate that 1) the clustering strategy enables fine-grained expert specialization with nearly 10% improvement in definition quality; 2) the semantic-aware domain-level routing mechanism achieves higher expert efficacy (+1%) than conventional token-level routing; and 3) further performance gains can be obtained through test-time compute and semantic expert scaling. Our work advances definition modeling while providing insights into the development of efficient language models for semantic-intensive applications.
title LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts
topic Computation and Language
url https://arxiv.org/abs/2602.14060