Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{200164,
        author = {Mahua Mukhopadhyay},
        title = {An Interpretable AI Framework for Resume Ranking via Hybrid NLP [3] and Large Language Models},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {564-572},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200164},
        abstract = {The increasing volume of job applications has made manual resume screening inefficient, time-consuming, and prone to inconsistency. Existing automated solutions largely rely on either keywork-based matching, which lacks contextual understanding, or large language model (LLM)-based approaches, which often suffer from limited interpretability and potential bias. To address these limitations, this paper proposes a hybrid framework that integrates traditional Natural Language Processing (NLP [3]) techniques with LLM- driven semantic analysis for automated resume ranking.
The proposed system processes curriculum vitas and job descriptions across multiple document formats, extracting structured features such as skills, experience, and qualifications using NLP [3] tools while simultaneously leveraging LLMs to capture contextual and semantic relationships.  A hybrid similarity scoring mechanism is introduced, combining keyword-based matching with embedding-based semantic similarity to generate robust candidate rankings. This approach enables improved alignment between candidate profiles and job requirements while maintaining interpretability in the ranking process
Experimental evaluation demonstrates that the proposed method achieves improved matching performance compared to traditional keyword-based systems and offers greater transparency than purely LLM-based approaches. The results highlight the effectiveness of combining symbolic and neural techniques in development of scalable, interpretable, and efficient AI- driven hiring system.[15]},
        keywords = {},
        month = {May},
        }