• Computer Science > Artificial Intelligence [Submitted on 26 Jan 2026] Title:A Geometric Taxonomy of Hallucinations in LLMs View PDF HTML (experimental)Abstract:The term “hallucination” in large language models conflates distinct phenomena with different geometric signatures in embedding space. • We propose a taxonomy identifying three types: unfaithfulness (failure to engage with provided context), confabulation (invention of semantically foreign content), and factual error (incorrect claims within correct conceptual frames). • We observe a striking asymmetry. • On standard benchmarks where hallucinations are LLM-generated, detection is domain-local: AUROC 0.76-0.99 within domains, but 0.50 (chance level) across domains. • Discriminative directions are approximately orthogonal between domains (mean cosine similarity -0.07). • On human-crafted confabulations - invented institutions, redefined terminology, fabricated mechanisms - a single global direction achieves 0.96 AUROC with 3.8% cross-domain degradation.
Article Summaries:
- Computer Science > Artificial Intelligence [Submitted on 26 Jan 2026] Title:A Geometric Taxonomy of Hallucinations in LLMs View PDF HTML (experimental)Abstract:The term “hallucination” in large language models conflates distinct phenomena with different geometric signatures in embedding space. We propose a taxonomy identifying three types: unfaithfulness (failure to engage with provided context), confabulation (invention of semantically foreign content), and factual error (incorrect claims within correct conceptual frames). We observe a striking asymmetry. On standard benchmarks where hallucin
Sources: