Blog · Tag
Posts tagged “hallucination”
2 posts
T
AI in Academia
The 2026 AI Citation Hallucination Benchmark: ChatGPT vs Claude vs Perplexity vs Elicit
A cross-tool benchmark of citation fabrication rates across ChatGPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro, Perplexity, Elicit, and Consensus. Preliminary results.
Apr 16, 202622 min read
W
AI in Academia
Why ChatGPT Makes Up Citations: The Technical Reason LLMs Hallucinate Sources
A technical explanation of why ChatGPT fabricates academic citations: token prediction, training data gaps, RLHF artifacts, and why retrieval changes everything.
Apr 16, 202614 min read