Research
impact 16
DO-Bench: An Attributable Benchmark for Diagnosing Object Hallucination in Vision-Language Models
DO-Bench: An Attributable Benchmark for Diagnosing Object Hallucination in Vision-Language Models arXiv:2604.22822v1 Announce Type: cross Abstract: Object level hallucination remains a central reliability challenge for…
Why it matters
Not an isolated event—object has been trending in this direction. The hallucination connection makes it particularly relevant.