aiqbench analysis
This research demonstrates how large language models can automate the creation of simplified dictionary definitions for learners, addressing the high cost of manual lexicography. By employing an LLM-as-a-judge evaluation framework and iterative simplification techniques, the study achieves results comparable to human annotators while maintaining lexical simplicity. The work advances natural language processing applications in education by providing a scalable solution for generating high-quality reference materials.
Towards Automated Lexicography: Generating and Evaluating Definitions for Learner's Dictionaries
arXiv:2601.01842v2 Announce Type: replace Abstract: Dictionary definitions are an essential resource for learning word senses, but manually creating them is costly. We thus study dictionary definition generation (DDG), i.e., the generation of non-contextualized definitions for given headwords. Specifically, we address learner's dictionary definition generation (LDDG), where definitions should be written using simple vocabulary. First, we introduce a reliable evaluation approach for DDG, based on newly proposed evaluation criteria and powered by an LLM-as-a-judge. To provide reference definitions for the evaluation, we construct a dataset of Japanese dictionary definitions in collaboration with a professional lexicographer. Validation results demonstrate that our evaluation approach agrees with human annotators at a level comparable to inter-annotator agreement. Second, we propose an LLM-based LDDG approach that employs iterative simplification. Experimental results show that our approach yields definitions that achieve high scores on the proposed criteria and exhibit high lexical simplicity.
Abstract:Dictionary definitions are an essential resource for learning word senses, but manually creating them is costly. We thus study dictionary definition generation (DDG), i.e., the generation of non-contextualized definitions for given headwords. Specifically, we address learner's dictionary definition generation (LDDG), where definitions should be written using simple vocabulary. First, we introduce a reliable evaluation approach for DDG, based on newly proposed evaluation criteria and powered by an LLM-as-a-judge. To provide reference definitions for the evaluation, we construct a dataset of Japanese dictionary definitions in collaboration with a professional lexicographer. Validation results demonstrate that our evaluation approach agrees with human annotators at a level comparable to inter-annotator agreement. Second, we propose an LLM-based LDDG approach that employs iterative simplification. Experimental results show that our approach yields definitions that achieve high scores on the proposed criteria and exhibit high lexical simplicity.
Computation and Language (cs.CL)
arXiv:2601.01842 [cs.CL]
(or arXiv:2601.01842v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2601.01842 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 232 words
Related coverage
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · Jun 12, 2026
Implications of Continual Learning for LLM Agents: Introduction
LessWrong · Jun 12, 2026
Presentation: From AI Agent Demo to Production: Automated Testing and Evaluation
InfoQ · Sep 7, 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026