# Discovering Lexical Gaps Using Embeddings from Multilingual LLMs

arXiv: https://arxiv.org/abs/2605.24310 · HTML: https://mlsanity.com/paper/2605.24310/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 50 references that are in the map.
- First posted on arXiv 23 May 2026.

## Builds on (most cited first, 10 of 10)

- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Multilingual Language Models are not Multicultural: A Case Study in Emotion](https://mlsanity.com/paper/2307.01370/) (2023)
- [Benchmarking Machine Translation with Cultural Awareness](https://mlsanity.com/paper/2305.14328/) (2023)
- [EXAONE 3.5: Series of Large Language Models for Real-world Use Cases](https://mlsanity.com/paper/2412.04862/) (2024)
- [Kanana: Compute-efficient Bilingual Language Models](https://mlsanity.com/paper/2502.18934/) (2025)
- [Concept Space Alignment in Multilingual LLMs](https://mlsanity.com/paper/2410.01079/) (2024)
- [Using Linguistic Typology to Enrich Multilingual Lexicons: the Case of Lexical Gaps in Kinship](https://mlsanity.com/paper/2204.05049/) (2022)
- [Exploring Dimensionality Reduction Techniques in Multilingual Transformers](https://mlsanity.com/paper/2204.08415/) (2022)
- [Lexical Diversity in Kinship Across Languages and Dialects](https://mlsanity.com/paper/2308.13056/) (2023)
- [Locally Measuring Cross-lingual Lexical Alignment: A Domain and Word Level Perspective](https://mlsanity.com/paper/2410.07239/) (2024)

## Abstract (arXiv)

Lexical gaps are words that do not exist in certain languages. They pose challenges for building multilingual lexical resources, for machine translation, and for cross-lingual transfer. Existing lexical gap detection relies on human judgments or fixed conceptual taxonomies. We propose a data-driven framework for identifying cross-lingual lexical gaps. We extracted contextualized embeddings from Korean-English bilingual LLMs for Korean-to-English and English-to-Korean translation pairs. Combinations of LLMs, embedding types, dimensionality, and orthogonal transformations across 100 train-test splits yielded 4000 distinct embedding spaces in each source language. In each space, we computed the semantic similarity between each source word and its nearest neighbor in the target language, and compared their distribution for gap words versus non-gap words. In 94% (Korean-to-English) and 97% (English-to-Korean) of embedding spaces, gap words showed weaker cross-lingual semantic alignment than non-gap words. Logistic classifiers trained on unaligned embedding spaces can reliably separate gap words from non-gap words, achieving AUCs of 0.81 (Korean-to-English) and 0.76 (English-to-Korean) and retrieving 18/19 Korean and 26/27 English gap words. This approach provides a language-agnostic and taxonomy-free method for scalable lexical gap identification.