How Well Do Large Language Models Disambiguate Swedish Words?

2024/10/30 by Richard Johansson, Johansson, Richard
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2410.22827

openalex publication_date 2024/10/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We evaluate a battery of recent large language models on two benchmarks for word sense disambiguation in Swedish. At present, all current models are less accurate than the best supervised disambiguators in cases where a training set is available, but most models outperform graph-based unsupervised systems. Different prompting approaches are compared, with a focus on how to express the set of possible senses in a given context. The best accuracies are achieved when human-written definitions of the senses are included in the prompts.

Related

• Exploring the Word Sense Disambiguation Capabilities of Large Language Models
• Uppsala NLP at SemEval-2021 Task 2: Multilingual Language Models for Fine-tuning and Feature Extraction in Word-in-Context Disambiguation
• Analysis and Evaluation of Language Models for Word Sense Disambiguation
• Word Sense Disambiguation for 158 Languages using Word Embeddings Only
• Language models in word sense disambiguation for Polish