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 Baseline reference
HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models
Baseline reference. 67% of citing Pith papers use this work as a benchmark or comparison.
26
Pith papers citing it
Baseline
67% of classified citations
abstract
We introduce HallusionBench, a comprehensive benchmark designed for the evaluation of image-context reasoning. This benchmark presents significant challenges to advanced large visual-language models (LVLMs), such as GPT-4V(Vision), Gemini Pro Vision, Claude 3, and LLaVA-1.5, by emphasizing nuanced understanding and interpretation of visual data. The benchmark comprises 346 images paired with 1129 questions, all meticulously crafted by human experts. We introduce a novel structure for these visual questions designed to establish control groups. This structure enables us to conduct a quantitative analysis of the models' response tendencies, logical consistency, and various failure modes. In our evaluation on HallusionBench, we benchmarked 15 different models, highlighting a 31.42% question-pair accuracy achieved by the state-of-the-art GPT-4V. Notably, all other evaluated models achieve accuracy below 16%. Moreover, our analysis not only highlights the observed failure modes, including language hallucination and visual illusion, but also deepens an understanding of these pitfalls. Our comprehensive case studies within HallusionBench shed light on the challenges of hallucination and illusion in LVLMs. Based on these insights, we suggest potential pathways for their future improvement. The benchmark and codebase can be accessed at https://github.com/tianyi-lab/HallusionBench.
hub tools
citation-role summary
dataset 6
background 3
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.
Visual Para-Thinker is the first parallel reasoning framework for MLLMs that uses visual partitioning strategies, Pa-Attention, and LPRoPE to extend test-time scaling benefits to visual comprehension tasks.
DMLR performs dynamic visual-textual interleaving in latent space using confidence-guided latent policy gradient optimization and a dynamic visual injection strategy, yielding improved multimodal reasoning on benchmarks.
FLARE is a vision-language model family using text-guided vision encoding, context-aware alignment decoding, dual-semantic mapping loss, and text-driven VQA synthesis to achieve deep cross-modal integration, outperforming larger models with only 630 vision tokens at 3B scale.
R1-VL uses StepGRPO with rule-based StepRAR and StepRVR rewards to let MLLMs learn step-by-step reasoning beyond imitation of positive paths.
MuirBench is a new benchmark showing that top multimodal LLMs struggle with robust multi-image understanding, with GPT-4o at 68% and open-source models below 33% accuracy.
POW3R adapts rubric criterion weights via rollout contrast in RLVR to improve mean reward, strict completion rates, and training speed over static rubric aggregation on multimodal and text tasks.
Vision-language models contain identifiable grounding and hallucination pathways; suppressing the latter reduces object hallucinations by up to 76% while preserving accuracy.
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
Argos is an agentic verifier that adaptively picks scoring functions to evaluate accuracy, localization, and reasoning quality, enabling stronger multimodal RL training for AI agents.
ViLoMem is a dual-stream grow-and-refine memory system that separates visual and logical error patterns in MLLMs to improve pass@1 accuracy and reduce repeated mistakes across six multimodal benchmarks.
InternVL3.5 advances open-source multimodal models with Cascade RL for +16% reasoning gains and ViR for 4x inference speedup, with the 241B model reaching SOTA among open-source MLLMs on multimodal, reasoning, and agentic tasks.
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.
InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
AMBER is an LLM-free multi-dimensional benchmark for evaluating hallucinations in MLLMs across generative and discriminative tasks.
A new dataset of 400k visual instructions including negative examples at three semantic levels reduces hallucinations in models like MiniGPT-4 when used for fine-tuning while improving benchmark performance.
Causal path-patching analysis across five MLLMs identifies distributed hallucination-driving attention heads and localized resisting heads whose imbalance biases generation toward erroneous text over visual evidence; a conditional intervention MACI suppresses the driving heads and cuts hallucination
CAAC mitigates hallucinations in LVLMs via Visual-Token Calibration and Adaptive Attention Re-Scaling guided by model confidence, showing gains on CHAIR, AMBER, and POPE especially in long-form generation.
Qwen2.5-VL reports a vision-language model family using native dynamic-resolution ViT and absolute time encoding that matches GPT-4o on document and diagram tasks while supporting hour-long videos with second-level localization.
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
InternVL 1.5 narrows the performance gap to proprietary multimodal models via a stronger transferable vision encoder, dynamic high-resolution tiling, and curated English-Chinese training data.
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.
-
Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension
Visual Para-Thinker is the first parallel reasoning framework for MLLMs that uses visual partitioning strategies, Pa-Attention, and LPRoPE to extend test-time scaling benefits to visual comprehension tasks.
-
Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
DMLR performs dynamic visual-textual interleaving in latent space using confidence-guided latent policy gradient optimization and a dynamic visual injection strategy, yielding improved multimodal reasoning on benchmarks.
-
FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding
FLARE is a vision-language model family using text-guided vision encoding, context-aware alignment decoding, dual-semantic mapping loss, and text-driven VQA synthesis to achieve deep cross-modal integration, outperforming larger models with only 630 vision tokens at 3B scale.
-
R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
R1-VL uses StepGRPO with rule-based StepRAR and StepRVR rewards to let MLLMs learn step-by-step reasoning beyond imitation of positive paths.
-
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
MuirBench is a new benchmark showing that top multimodal LLMs struggle with robust multi-image understanding, with GPT-4o at 68% and open-source models below 33% accuracy.
-
Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR
POW3R adapts rubric criterion weights via rollout contrast in RLVR to improve mean reward, strict completion rates, and training speed over static rubric aggregation on multimodal and text tasks.
-
Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
Vision-language models contain identifiable grounding and hallucination pathways; suppressing the latter reduces object hallucinations by up to 76% while preserving accuracy.
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
-
Multimodal Reinforcement Learning with Adaptive Verifier for AI Agents
Argos is an agentic verifier that adaptively picks scoring functions to evaluate accuracy, localization, and reasoning quality, enabling stronger multimodal RL training for AI agents.
-
Agentic Learner with Grow-and-Refine Multimodal Semantic Memory
ViLoMem is a dual-stream grow-and-refine memory system that separates visual and logical error patterns in MLLMs to improve pass@1 accuracy and reduce repeated mistakes across six multimodal benchmarks.
-
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
InternVL3.5 advances open-source multimodal models with Cascade RL for +16% reasoning gains and ViR for 4x inference speedup, with the 241B model reaching SOTA among open-source MLLMs on multimodal, reasoning, and agentic tasks.
-
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.
-
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
InternVL3-78B sets a new open-source SOTA of 72.2 on MMMU via native joint multimodal pre-training, V2PE, MPO, and test-time scaling while remaining competitive with proprietary models.
-
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
-
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.
-
Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
A new dataset of 400k visual instructions including negative examples at three semantic levels reduces hallucinations in models like MiniGPT-4 when used for fine-tuning while improving benchmark performance.
-
Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination
Causal path-patching analysis across five MLLMs identifies distributed hallucination-driving attention heads and localized resisting heads whose imbalance biases generation toward erroneous text over visual evidence; a conditional intervention MACI suppresses the driving heads and cuts hallucination
-
Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration
CAAC mitigates hallucinations in LVLMs via Visual-Token Calibration and Adaptive Attention Re-Scaling guided by model confidence, showing gains on CHAIR, AMBER, and POPE especially in long-form generation.
-
Qwen2.5-VL Technical Report
Qwen2.5-VL reports a vision-language model family using native dynamic-resolution ViT and absolute time encoding that matches GPT-4o on document and diagram tasks while supporting hour-long videos with second-level localization.
-
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.
-
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
-
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
InternVL 1.5 narrows the performance gap to proprietary multimodal models via a stronger transferable vision encoder, dynamic high-resolution tiling, and curated English-Chinese training data.
- Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models
- To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs