When LLM Meets Fuzzy-TOPSIS for Personnel Selection Through Automated Profile Analysis

2026-01-30

IEEE Access

AI Summary

This study addresses the challenge of efficiently, objectively, and scalably screening candidates for software engineering roles by proposing LLM-TOPSIS, a novel framework that integrates large language models with fuzzy multi-criteria decision-making. The approach leverages a fine-tuned DistilRoBERTa model to automatically parse LinkedIn profiles and extract multidimensional criteria—including education, experience, and skills—while employing triangular fuzzy numbers to capture evaluation uncertainty. Candidate rankings are then generated through Fuzzy TOPSIS for comprehensive scoring and ordering. Experimental results demonstrate that the system achieves 91% accuracy in assessing experience and overall attributes, with ranking outcomes showing strong alignment with expert evaluations. By combining linguistic understanding with robust decision theory, the framework enhances objectivity, scalability, consistency, and fairness in technical hiring processes.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Natural Language Processing: Information Extraction
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

In this highly competitive employment environment, the selection of suitable personnel is essential for organizational success. This study presents an automated personnel selection system that utilizes sophisticated natural language processing (NLP) methods to assess and rank software engineering applicants. A distinctive dataset was created by aggregating LinkedIn profiles that include essential features such as education, work experience, abilities, and self-introduction, further enhanced with expert assessments to function as standards. The research combines large language models (LLMs) with multicriteria decision-making (MCDM) theory to develop the LLM-TOPSIS framework. In this context, we utilized the TOPSIS method enhanced by fuzzy logic (Fuzzy TOPSIS) to address the intrinsic ambiguity and subjectivity in human assessments. We utilized triangular fuzzy numbers (TFNs) to describe criteria weights and scores, thereby addressing the ambiguity frequently encountered in candidate evaluations. For candidate ranking, the DistilRoBERTa model was fine-tuned and integrated with the fuzzy TOPSIS method, achieving rankings closely aligned with human expert evaluations and attaining an accuracy of up to 91% for the Experience attribute and the Overall attribute. The study underlines the potential of NLP-driven frameworks to improve recruitment procedures by boosting scalability, consistency, and minimizing prejudice. Future endeavors will concentrate on augmenting the dataset, enhancing model interpretability, and verifying the system in actual recruitment scenarios to better evaluate its practical applicability. This research highlights the intriguing potential of merging NLP with fuzzy decision-making methods in personnel selection, enabling scalable and unbiased solutions to recruitment difficulties.

Problem

• personnel selection
• fuzzy decision-making
• natural language processing
• candidate evaluation
• recruitment bias

Innovation

• Large Language Models
• Fuzzy TOPSIS
• Personnel Selection
• Natural Language Processing
• Multicriteria Decision-Making