LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts

TL;DR

LM-Lexicon introduces a semantic expert-based approach for definition modeling, leveraging clustering and model merging to significantly improve performance on benchmark datasets.

Contribution

It proposes a novel sparse mixture-of-experts architecture with semantic domain specialization, achieving state-of-the-art results in definition modeling.

Findings

Clustering enables fine-grained expert specialization with 10% better definition quality.

Semantic-aware routing outperforms token-level routing by 1%.

Scaling experts and compute at test time further improves performance.

Abstract

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.