Simplifications are Absolutists: How Simplified Language Reduces Word Sense Awareness in LLM-Generated Definitions
Preprint
Abstract
Large Language Models (LLMs) can provide accurate word definitions and explanations for any context. However, the scope of the definition changes for different target groups, like children or language learners. This is especially relevant for homonyms, words with multiple meanings, where oversimplification might risk information loss by omitting key senses, potentially misleading users who trust LLM outputs. We investigate how simplification impacts homonym definition quality across three target groups: Normal, Simple, and ELI5. Using two novel evaluation datasets spanning multiple languages, we test DeepSeek v3, Llama 4 Maverick, Qwen3-30B A3B, GPT-4o mini, and Llama 3.1 8B via LLM-as-Judge and human annotations. Our results show that simplification drastically degrades definition completeness by neglecting polysemy, increasing the risk of misunderstanding. Fine-tuning Llama 3.1 8B with Direct Preference Optimization substantially improves homonym response quality across all prompt types. These findings highlight the need to balance simplicity and completeness in educational NLP to ensure reliable, context-aware definitions for all learners.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Large Language Models for Education: A survey and outlookIEEE Signal Processing Magazine, 2026
- Easy-read and large language models: on the ethical dimensions of LLM-based text simplificationEthics and Information Technology, 2024
- Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading ComprehensionTransactions of the Association for Computational Linguistics, 2024
- ChatGPT for good? On opportunities and challenges of large language models for educationLearning and Individual Differences, 2023
- Approaches to simplifying academic texts in English: English teachers’ views and practicesEnglish for Specific Purposes, 2022
- ConceptNet 5.5: An Open Multilingual Graph of General KnowledgeProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Definition Modeling: Learning to Define Word Embeddings in Natural LanguageProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Word sense disambiguationACM Computing Surveys, 2009
- "I Don’t Believe in Word Senses"Computers and the Humanities, 1997
- A new readability yardstick.Journal of Applied Psychology, 1948