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{198807,
        author = {Tejas Gogawale and Kiran Ingale and Aniket Dhingra and Aaryan Deshmukh and Shravani Dixit and Harsh Sharma},
        title = {EvaloAI – Instant, Unbiased Grading Powered By AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {10909-10917},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198807},
        abstract = {The rise of digital and AI-assisted writing tools has increased the need for automated evaluation systems that ensure both accuracy and academic integrity. This paper presents EvaloAI, an intelligent online grading framework that unifies handwriting recognition, semantic answer evaluation, plagiarism detection, and AI-generated content identification in a single pipeline. The system extracts typed and handwritten responses using OCR via Google Vision and Tesseract, aligns them with corresponding questions, and evaluates answers using a hybrid scoring mechanism combining keyword detection, phrase overlap, BERTScore semantic similarity, and grammar analysis. To preserve academic integrity, EvaloAI incorporates a plagiarism detection module based on TF-IDF cosine similarity, SequenceMatcher alignment, n-gram overlap, and optional Google Custom Search queries for external web plagiarism. Additionally, an AI-generated content detector evaluates perplexity, burstiness, sentence uniformity, and common LLM writing patterns, with optional support for external APIs such as sapling AI. Experimental results show that EvaloAI provides consistent scoring, reliable semantic interpretation, and robust detection of both copied and AI- generated answers. The system offers a scalable, end-to-end solution for modern automated assessment environments.},
        keywords = {OCR, Plagiarism Detection, BERTScore, NLP, AI-generated},
        month = {April},
        }