NLPnorth @ TalentCLEF 2025: Comparing Discriminative, Contrastive, and Prompt-Based Methods for Job Title and Skill Matching

TL;DR

This paper compares discriminative, contrastive, and prompt-based methods for multilingual job title and skill matching, showing prompt-based approaches excel in job title matching and large multilingual models perform best overall.

Contribution

It provides a comprehensive comparison of different fine-tuning and prompting methods for job title and skill matching across multiple languages.

Findings

Prompting method achieved highest MAP in job title matching.

Fine-tuned classification performed best for skill prediction.

Large multilingual models outperformed smaller models.

Abstract

Matching job titles is a highly relevant task in the computational job market domain, as it improves e.g., automatic candidate matching, career path prediction, and job market analysis. Furthermore, aligning job titles to job skills can be considered an extension to this task, with similar relevance for the same downstream tasks. In this report, we outline NLPnorth's submission to TalentCLEF 2025, which includes both of these tasks: Multilingual Job Title Matching, and Job Title-Based Skill Prediction. For both tasks we compare (fine-tuned) classification-based, (fine-tuned) contrastive-based, and prompting methods. We observe that for Task A, our prompting approach performs best with an average of 0.492 mean average precision (MAP) on test data, averaged over English, Spanish, and German. For Task B, we obtain an MAP of 0.290 on test data with our fine-tuned classification-based approach. Additionally, we made use of extra data by pulling all the language-specific titles and corresponding \emph{descriptions} from ESCO for each job and skill. Overall, we find that the largest multilingual language models perform best for both tasks. Per the provisional results and only counting the unique teams, the ranking on Task A is 5$^{\text{th}}$/20 and for Task B 3$^{\text{rd}}$/14.