HallusionBench

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination & Visual Illusion in Large Vision-Language Models You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models Tianrui Guan*, Fuxiao Liu*

Papers using HallusionBench (6)

GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models2026ACPO: Counteracting Likelihood Displacement in Vision-Language Alignment with Asymmetric Constraints2026Beyond Dominant Patches: Spatial Credit Redistribution For Grounded Vision-Language Models2026CoRGI: Verified Chain-of-Thought Reasoning with Post-hoc Visual Grounding2025OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles2025EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation2024