Detecting AI-Generated Scientific Abstracts Using Galactica and Graph Neural Networks

Simple item page
dc.contributor.authorPathak, Anurag
dc.contributor.authorSharma, Dilip Kumar
dc.contributor.authorAgrawal, Harshada
dc.contributor.authorChawuthai, Rathachai
dc.contributor.authorPetchhan, Jirayu
dc.date.accessioned2026-08-06T10:48:36Z
dc.date.available2026-08-06T10:48:36Z
dc.date.issued2025-01-01
dc.description.abstractThe rise of large language models has introduced new challenges in maintaining research integrity, particularly through the potential proliferation of AI-generated scientific content. This paper presents a novel hybrid framework that combines Galactica-a scientific language model developed by Meta AI-with Graph Neural Networks (GNNs) to detect AI-generated research abstracts. Leveraging the AI-GA dataset comprising 28,662 labeled abstracts, we extract domain-specific semantic embeddings using Galactica and construct a semantic similarity graph to approximate citation-like relationships. A two- layer GCN is then trained to classify each abstract as human- or AI-authored. Experimental results demonstrate that our method outperforms traditional baselines such as TF-IDF, RoBERTa, and perplexity-based detectors, while offering interpretable and scalable detection suitable for editorial screening pipelines.
dc.identifier.citation2025 7th International Conference on Information Systems and Computer Networks Iscon 2025, 2025
dc.identifier.doi10.1109/ISCON65210.2025.11341445
dc.identifier.other2-s2.0-105033350207
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/16289
dc.source2025 7th International Conference on Information Systems and Computer Networks Iscon 2025
dc.subjectAI-GA Dataset
dc.subjectCitation Graphs
dc.subjectFake Paper Detection
dc.subjectGalactica
dc.subjectGraph Neural Networks
dc.subjectResearch Integrity
dc.subjectSemantic Embeddings
dc.titleDetecting AI-Generated Scientific Abstracts Using Galactica and Graph Neural Networks
dc.typeConference Paper

Files

Collections

Research