AutoScreen-FW: An LLM-based Framework for Resume Screening
arXiv:2603.18390v1 Announce Type: new Abstract: Corporate recruiters often need to screen many resumes within a limited time, which increases their burden and may cause suitable candidates to be overlooked. To address these challenges, prior work has explored LLM-based automated resume screening. However, some methods rely on commercial LLMs, which may pose data privacy risks. Moreover, since companies typically do not make resumes with evaluation results publicly available, it remains unclear which resume samples should be used during learning to improve an LLM's judgment performance. To address these problems, we propose AutoScreen-FW, an LLM-based locally and automatically resume screening framework. AutoScreen-FW uses several methods to select a small set of representative resume samples. These samples are used for in-context learning together with a persona description and evaluation criteria, enabling open-source LLMs to act as a career advisor and evaluate unseen resumes. Exper
arXiv:2603.18390v1 Announce Type: new Abstract: Corporate recruiters often need to screen many resumes within a limited time, which increases their burden and may cause suitable candidates to be overlooked. To address these challenges, prior work has explored LLM-based automated resume screening. However, some methods rely on commercial LLMs, which may pose data privacy risks. Moreover, since companies typically do not make resumes with evaluation results publicly available, it remains unclear which resume samples should be used during learning to improve an LLM's judgment performance. To address these problems, we propose AutoScreen-FW, an LLM-based locally and automatically resume screening framework. AutoScreen-FW uses several methods to select a small set of representative resume samples. These samples are used for in-context learning together with a persona description and evaluation criteria, enabling open-source LLMs to act as a career advisor and evaluate unseen resumes. Experiments with multiple ground truths show that the open-source LLM judges consistently outperform GPT-5-nano. Under one ground truth setting, it also surpass GPT-5-mini. Although it is slightly weaker than GPT-5-mini under other ground-truth settings, it runs substantially faster per resume than commercial GPT models. These findings indicate the potential for deploying AutoScreen-FW locally in companies to support efficient screening while reducing recruiters' burden.
Executive Summary
This article proposes AutoScreen-FW, an LLM-based framework for resume screening that addresses data privacy risks and selection of representative resume samples. The framework uses open-source LLMs to evaluate unseen resumes with improved performance compared to commercial models. The results indicate potential for deploying AutoScreen-FW locally in companies for efficient screening and reducing recruiters' burden. The findings suggest that open-source LLMs can be a viable alternative to commercial models, offering better performance and faster processing times. However, the framework's performance may vary depending on the ground truth settings, and further research is needed to fully explore its potential.
Key Points
- ▸ AutoScreen-FW addresses data privacy risks and selection of representative resume samples
- ▸ Open-source LLMs outperform commercial models in resume screening
- ▸ Framework offers faster processing times compared to commercial models
Merits
Data privacy enhancement
By using open-source LLMs, AutoScreen-FW reduces the risk of data breaches associated with commercial models.
Improved performance
The framework's use of in-context learning and persona descriptions enables open-source LLMs to outperform commercial models in resume screening.
Efficient processing
AutoScreen-FW's open-source nature allows for faster processing times compared to commercial models, making it a more practical solution for companies.
Demerits
Ground truth dependence
The framework's performance may vary depending on the ground truth settings, which can affect its overall effectiveness.
Limited scalability
While AutoScreen-FW is suitable for small- to medium-sized companies, its scalability for large corporations remains uncertain.
Expert Commentary
The article presents a promising solution to the challenges of resume screening, but further research is needed to fully explore its potential. The use of open-source LLMs is a significant advancement, but the framework's performance may vary depending on the ground truth settings. Moreover, the scalability of AutoScreen-FW for large corporations remains uncertain. Nevertheless, the framework's ability to address data privacy risks and offer faster processing times makes it a viable alternative to commercial models. As the use of LLMs in hiring tools continues to grow, policymakers and companies must consider the implications of these tools on the hiring process and the broader workforce.
Recommendations
- ✓ Further research is needed to explore the scalability of AutoScreen-FW for large corporations.
- ✓ Policymakers should consider the implications of LLMs in job screening and hiring processes.
