arXiv cs.AI· Hazrat Ali, Mohamed Elawady·· 13 小时前AI 评分27
Fabrication Severity Stack：用主流 LLM 界面零成本检测论文伪造引用
Zero-Cost Detection of Fabricated Citations: A Staged Heuristic Approach for Computing Dissertation Assessment
AI 导读
研究者提出 Fabrication Severity Stack（FSS）三级框架，按检测难度对引用伪造分类，并基于该框架设计了一套可通过主流 LLM 界面执行的分阶段启发式核验流程。
正文 · 原文
Abstract:Generative AI's growing role in academic writing has driven a rise in fabricated references across dissertations and student reports. We present the Fabrication Severity Stack (FSS), a three-tiered framework classifying citation fabrications by detection complexity - from non-existent references to subtle content misattribution. Building on the FSS, we propose a staged heuristic verification workflow, executable through mainstream LLM interfaces. We argue that this framework offers computer science educators/examiners a practical, zero-cost basis for embedding reference verification into the assessment of dissertation and students' reports. In a pilot study on 100 citations (20% seeded with Level 1 and Level 2 fabrications), the proposed heuristic workflow enabled mainstream LLM interfaces to correctly flag 9-10 of 10 non-existent references and partially detect metadata corruption. These preliminary results suggest that freely accessible, general-purpose LLMs can achieve high recall on citation verification without reliance on proprietary detection tools.
| Comments: | 2 pages abstract, submitted to ACM SIGCSE-virtual conference |
| Subjects: | Digital Libraries (cs.DL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.28649 [cs.DL] |
| (or arXiv:2610.28649v1 [cs.DL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.28649 arXiv-issued DOI via DataCite |
Submission history
From: Hazrat Ali [view email]
[v1]
Mon, 5 Oct 2026 21:13:57 UTC (30 KB)
来源：arXiv cs.AI · arxiv.org