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.
hub Mixed citations
Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
Mixed citation behavior. Most common role is background (59%).
38
Pith papers citing it
Background
59% of classified citations
abstract
Despite the promising progress in multi-modal tasks, current large multi-modal models (LMMs) are prone to hallucinating inconsistent descriptions with respect to the associated image and human instructions. This paper addresses this issue by introducing the first large and diverse visual instruction tuning dataset, named Large-scale Robust Visual (LRV)-Instruction. Our dataset comprises 400k visual instructions generated by GPT4, covering 16 vision-and-language tasks with open-ended instructions and answers. Unlike existing studies that primarily focus on positive instruction samples, we design LRV-Instruction to include both positive and negative instructions for more robust visual instruction tuning. Our negative instructions are designed at three semantic levels: (i) Nonexistent Object Manipulation, (ii) Existent Object Manipulation and (iii) Knowledge Manipulation. To efficiently measure the hallucination generated by LMMs, we propose GPT4-Assisted Visual Instruction Evaluation (GAVIE), a stable approach to evaluate visual instruction tuning like human experts. GAVIE does not require human-annotated groundtruth answers and can adapt to diverse instruction formats. We conduct comprehensive experiments to investigate the hallucination of LMMs. Our results demonstrate existing LMMs exhibit significant hallucinations when presented with our negative instructions, particularly Existent Object and Knowledge Manipulation instructions. Moreover, we successfully mitigate hallucination by finetuning MiniGPT4 and mPLUG-Owl on LRV-Instruction while improving performance on several public datasets compared to state-of-the-art methods. Additionally, we observed that a balanced ratio of positive and negative instances in the training data leads to a more robust model. Code and data are available at https://github.com/FuxiaoLiu/LRV-Instruction.
hub tools
citation-role summary
background 9
dataset 6
baseline 1
method 1
citation-polarity summary
representative citing papers
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
Prefill-Time Intervention (PTI) reduces hallucinations in large vision-language models by applying a one-time modality-aware steering correction to the initial KV cache at the prefill stage rather than during autoregressive decoding.
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%.
CAST reduces object hallucination in LVLMs by 6.03% on average across five models and five benchmarks by identifying caption-sensitive attention heads and applying optimized steering directions to their outputs, with negligible added inference cost.
OSCAR exploits the generative-discriminative gap in LVLMs to build online preference data with MCTS and dual-granularity rewards for DPO-based calibration, claiming SOTA hallucination reduction and improved multimodal performance.
MLLMs ignore dial state geometry and cluster by appearance, causing inconsistency under variations; TriSCA's state-distance alignment, metadata supervision, and objective alignment improve robustness on clock and gauge benchmarks.
ReflectCAP distills model-specific hallucination and oversight patterns into Structured Reflection Notes that steer LVLMs toward more factual and complete image captions, reaching the Pareto frontier on factuality-coverage trade-offs.
FaithLens, an 8B-parameter model, detects faithfulness hallucinations with explanations and outperforms GPT-5.2 and o3 on 12 tasks after synthetic data curation and rule-based reinforcement learning.
MedGRPO applies cross-dataset reward normalization and a clinical LLM judge within multi-task RL to improve vision-language models on heterogeneous medical video understanding tasks using the new MedVidBench dataset.
TARS uses token-adaptive min-max preference optimization and FFT-based spectral regularization to cut hallucination rates in MLLMs from 26.4% to 13.2% with only 4.8k samples, outperforming standard DPO and larger data-augmented baselines.
SENTINEL reduces MLLM object hallucinations by over 90% via sentence-level early intervention with detector-bootstrapped preference data and C-DPO loss, outperforming prior SOTA on hallucination and capability benchmarks.
PCD redirects robotic policies toward object-relevant visual features via contrastive decoding on masked inputs, improving generalization without retraining or weight access.
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.
MoE-LLaVA applies mixture-of-experts sparsity to LVLMs via MoE-Tuning, delivering LLaVA-1.5-7B level visual understanding and better hallucination resistance with only ~3B active parameters.
LURE reduces object hallucination in LVLMs by 23% via post-hoc revision informed by co-occurrence, uncertainty, and text position analysis.
MME is a manually annotated benchmark evaluating MLLMs on perception and cognition across 14 subtasks to avoid data leakage and support fair model comparisons.
Otter is a multi-modal model instruction-tuned on the MIMIC-IT dataset of over 3 million in-context instruction-response pairs to improve convergence and generalization on tasks with multiple images and videos.
MESA reduces hallucinations in LVLMs via controlled selective latent intervention that preserves the original token distribution.
NVILA improves on VILA with a scale-then-compress visual token strategy and full-lifecycle efficiency optimizations, matching or exceeding leading VLMs on image and video benchmarks while reducing training cost 1.9-5.1x and latencies 1.2-2.8x.
mPLUG-Owl3 introduces hyper attention blocks to integrate vision and language for long image-sequence understanding and reports SOTA results on single-image, multi-image, and video benchmarks.
LLaVA-OneVision is the first single open LMM to simultaneously achieve strong performance in single-image, multi-image, and video scenarios with cross-scenario transfer capabilities.
MiniCPM-Llama3-V 2.5 delivers GPT-4V-level multimodal performance on phones through architecture, pretraining, and alignment optimizations.
The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.
citing papers explorer
No citing papers match the current filters.