← Back to Course Contents · ← All Papers
Week 5

AI-Assisted Literature Reviews

Tools, the hallucinated-citation crisis, and AI-augmented research workflows

5 papers covering hallucination rates across legal, medical and scientific contexts plus systematic-review screening. Most other Week 5 references are tool documentation rather than primary papers.

All PDFs link to raw.githubusercontent.com; clicking will download the file directly. Source links go to the canonical version on arXiv, the journal, or the publisher.

5.1 · The AI Literature Review Landscape

Assessing the Ability of ChatGPT to Screen Articles for Systematic Reviews
Syriani, E., David, I., & Kumar, G. (2023)

5.2 · Free Tools Deep Dive

Covers Semantic Scholar, ResearchRabbit, Connected Papers, NotebookLM, Google Scholar — tools, not papers.

5.3 · Paid Tools and When They Are Worth It

Covers Elicit, Consensus, Scite.ai, SciSpace, Litmaps Premium — tools, not papers.

5.4 · The Hallucinated Citation Crisis

Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools
Magesh, V., Surani, F., Dahl, M., Suzgun, M., Manning, C. D., & Ho, D. E. (2024) — Stanford HAI
Hallucination Rates and Reference Accuracy of ChatGPT and Bard for Systematic Reviews
Chelli, M., Descamps, J., Lavoué, V., et al. (2024) — JMIR 26: e53164
Hallucinations in AI-Generated References for Mental Health Literature Reviews
Linardon, J., et al. (2025) — JMIR Mental Health 12: e80371
Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy
Niimi, J. (2025)

5.5 · Building Your Research Workflow with Claude

Original workflow content.

5.6 · Hands-On Activities and Assessment

Assessment design.