A Taxonomy of Confabulations and the Perception-Reality Gap in LLM-Assisted Immersive Scene Editing
3.60T1 sourcearXiv cs.HC
arXiv cs.HCoriginal source ↗
Source record
Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2607.23213.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryA study with 24 non-expert users develops a taxonomy of LLM confabulations in immersive 3D scene editing, reports their prevalence and disruptiveness, and defines the perception-reality gap between actual and perceived confabulation occurrences, concluding with design implications for mitigation.
Why it mattersEmpirical taxonomy grounded in user observation gives system designers a concrete vocabulary for confabulation types in immersive LLM tools, beyond generic hallucination discussion.
Cited by
No citations on record.