MMMU-Pro is a stricter multimodal benchmark that removes text-only solvable questions, augments options, and requires reading text from images, yielding substantially lower model scores of 16.8-26.9%.
hub Canonical reference
Holistic analysis of hallucination in gpt-4v (ision): Bias and interference chal- lenges
Canonical reference. 71% of citing Pith papers cite this work as background.
16
Pith papers citing it
Background
71% of classified citations
hub tools
citation-role summary
background 4
baseline 1
dataset 1
method 1
citation-polarity summary
representative citing papers
MMMU provides 11.5K heterogeneous college-level multimodal questions that current models solve at 56-59% accuracy, establishing a new standard for expert multimodal evaluation.
The study links three LVLM architectural dimensions to three hallucination types via a new benchmark, finding that language foundation quality reduces co-occurrence errors, visual encoder strength reduces similarity errors, alignment reduces uncertainty errors, and joint visual-alignment improvement
Ghost-100 benchmark shows prompt tone drives hallucination rates and intensities in VLMs, with non-monotonic peaks at intermediate pressure and task-specific differences that aggregate metrics hide.
MMSearch-R1 uses reinforcement learning to train multimodal models for on-demand multi-turn internet search with image and text tools, outperforming same-size RAG baselines and matching larger ones while cutting search calls by over 30%.
HallusionBench shows GPT-4V reaches only 31.42% accuracy on paired questions testing language hallucination and visual illusion in LVLMs, with other models below 16%.
COAST prunes 77.8% of visual tokens in LVLMs with a 2.15x speedup while keeping 98.64% of original performance by adaptively routing semantic and spatial context via contrastive scores.
R-CoV is a six-step region-aware chain-of-verification technique that elicits coordinate and description outputs from LVLMs themselves to detect and reduce object hallucinations without external models or retraining.
OutSafe-Bench supplies the first large-scale four-modality safety dataset and evaluation framework that exposes persistent unsafe outputs in nine leading multimodal LLMs.
The work identifies a small set of attention heads in VLMs that mediate conflicts between parametric knowledge and visual input, and shows that intervening on them steers model behavior while attention patterns provide precise image-region attribution.
AMBER is an LLM-free multi-dimensional benchmark for evaluating hallucinations in MLLMs across generative and discriminative tasks.
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.
MolSight integrates a Molecular Topology Module and Molecular Grounding Module into VLMs to enhance molecular image understanding and claims to outperform prior models on chemical visual tasks.
A survey on LLM-as-a-Judge that reviews reliability strategies, proposes evaluation methods, and introduces a novel benchmark for assessing such systems.
citing papers explorer
-
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
MMMU-Pro is a stricter multimodal benchmark that removes text-only solvable questions, augments options, and requires reading text from images, yielding substantially lower model scores of 16.8-26.9%.
-
MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
MMMU provides 11.5K heterogeneous college-level multimodal questions that current models solve at 56-59% accuracy, establishing a new standard for expert multimodal evaluation.
-
What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness
The study links three LVLM architectural dimensions to three hallucination types via a new benchmark, finding that language foundation quality reduces co-occurrence errors, visual encoder strength reduces similarity errors, alignment reduces uncertainty errors, and joint visual-alignment improvement
-
LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models
Ghost-100 benchmark shows prompt tone drives hallucination rates and intensities in VLMs, with non-monotonic peaks at intermediate pressure and task-specific differences that aggregate metrics hide.
-
MMSearch-R1: Incentivizing LMMs to Search
MMSearch-R1 uses reinforcement learning to train multimodal models for on-demand multi-turn internet search with image and text tools, outperforming same-size RAG baselines and matching larger ones while cutting search calls by over 30%.
-
HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models
HallusionBench shows GPT-4V reaches only 31.42% accuracy on paired questions testing language hallucination and visual illusion in LVLMs, with other models below 16%.
-
Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models
COAST prunes 77.8% of visual tokens in LVLMs with a 2.15x speedup while keeping 98.64% of original performance by adaptively routing semantic and spatial context via contrastive scores.
-
R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
R-CoV is a six-step region-aware chain-of-verification technique that elicits coordinate and description outputs from LVLMs themselves to detect and reduce object hallucinations without external models or retraining.
-
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models
OutSafe-Bench supplies the first large-scale four-modality safety dataset and evaluation framework that exposes persistent unsafe outputs in nine leading multimodal LLMs.
-
When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models
The work identifies a small set of attention heads in VLMs that mediate conflicts between parametric knowledge and visual input, and shows that intervening on them steers model behavior while attention patterns provide precise image-region attribution.
-
AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
AMBER is an LLM-free multi-dimensional benchmark for evaluating hallucinations in MLLMs across generative and discriminative tasks.
-
Hallucination of Multimodal Large Language Models: A Survey
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
-
Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.
-
MolSight: A Graph-Aware Vision-Language Model for Unified Chemical Image Understanding
MolSight integrates a Molecular Topology Module and Molecular Grounding Module into VLMs to enhance molecular image understanding and claims to outperform prior models on chemical visual tasks.
-
A Survey on LLM-as-a-Judge
A survey on LLM-as-a-Judge that reviews reliability strategies, proposes evaluation methods, and introduces a novel benchmark for assessing such systems.
- Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models