Simplifications are Absolutists: How Simplified Language Reduces Word Sense Awareness in LLM-Generated Definitions

TL;DR

This paper examines how simplified language in LLM-generated definitions reduces the awareness of multiple word senses, risking information loss especially for homonyms, and evaluates methods to improve definition quality across different target groups.

Contribution

It introduces novel multilingual datasets and evaluates the impact of simplification on homonym definitions, proposing fine-tuning techniques to enhance definition completeness.

Findings

Simplification significantly reduces sense coverage in definitions.

Fine-tuning Llama 3.1 improves homonym response quality.

Simplification increases the risk of user misunderstanding.

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.