CCTVBench exposes a large gap between standard QA accuracy and contrastive consistency in traffic video reasoning for multimodal LLMs and introduces C-TCD to narrow that gap.
hub Canonical reference
Aligning Large Multimodal Models with Factually Augmented RLHF
Canonical reference. 72% of citing Pith papers cite this work as background.
43
Pith papers citing it
Background
72% of classified citations
abstract
Large Multimodal Models (LMM) are built across modalities and the misalignment between two modalities can result in "hallucination", generating textual outputs that are not grounded by the multimodal information in context. To address the multimodal misalignment issue, we adapt the Reinforcement Learning from Human Feedback (RLHF) from the text domain to the task of vision-language alignment, where human annotators are asked to compare two responses and pinpoint the more hallucinated one, and the vision-language model is trained to maximize the simulated human rewards. We propose a new alignment algorithm called Factually Augmented RLHF that augments the reward model with additional factual information such as image captions and ground-truth multi-choice options, which alleviates the reward hacking phenomenon in RLHF and further improves the performance. We also enhance the GPT-4-generated training data (for vision instruction tuning) with previously available human-written image-text pairs to improve the general capabilities of our model. To evaluate the proposed approach in real-world scenarios, we develop a new evaluation benchmark MMHAL-BENCH with a special focus on penalizing hallucinations. As the first LMM trained with RLHF, our approach achieves remarkable improvement on the LLaVA-Bench dataset with the 94% performance level of the text-only GPT-4 (while previous best methods can only achieve the 87% level), and an improvement by 60% on MMHAL-BENCH over other baselines. We opensource our code, model, data at https://llava-rlhf.github.io.
hub tools
citation-role summary
background 12
dataset 4
baseline 1
method 1
citation-polarity summary
representative citing papers
ErrorRadar is a new benchmark of 2,500 multimodal K-12 math problems for MLLM error step identification and categorization, where GPT-4o trails human experts by ~10%.
BRACS is a barrier-regulated adaptive closed-form steering framework that reduces hallucinations in LVLMs by intervening on hidden states based on attention-measured grounding failure.
A reinforcement-learned vision-language agent adaptively selects and fuses monocular depth experts per sample for better performance across camera geometries.
OxyEcomBench is a unified multimodal benchmark covering 6 capability areas and 29 tasks with authentic e-commerce data to measure how well foundation models handle real platform, merchant, and customer challenges.
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.
GPS trains a small model on optimization history to predict prompt difficulty and select intermediate-difficulty diverse batches, yielding better training efficiency, final performance, and test-time allocation than baselines on reasoning benchmarks.
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
Chain-of-Zoom factorizes extreme super-resolution into an autoregressive sequence of intermediate scales using a reused backbone model plus GRPO-tuned multi-scale VLM prompts.
UnifiedReward is the first unified reward model that jointly assesses multimodal understanding and generation to provide better preference signals for aligning vision models via DPO.
Reweighting training emphasis toward image-negative tokens and filtering hallucinated data reduces object hallucination in LVLMs across three model variants.
Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.
Vision-language models contain identifiable grounding and hallucination pathways; suppressing the latter reduces object hallucinations by up to 76% while preserving accuracy.
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.
MiniCPM-o 4.5 uses the Omni-Flow streaming framework to deliver real-time full-duplex omni-modal interaction with proactive behavior in a 9B model that approaches Gemini 2.5 Flash performance.
Hallucinations in LVLMs largely arise from textual priors in prompts, and can be reduced by fine-tuning with preference optimization on grounded vs. hallucinated response pairs.
S2H-DPO generates hierarchical prompt-driven preference pairs to improve multi-image reasoning in VLMs while keeping single-image performance intact.
PSRD mitigates visual hallucinations in LVLMs via phase-wise self-reward decoding, cutting rates by 50% on LLaVA-1.5-7B and outperforming prior methods on five benchmarks.
DACO curates a 15,000-concept dictionary from 400K image-caption pairs and uses it to initialize an SAE that enables granular, concept-specific steering of MLLM activations, raising safety scores on MM-SafetyBench and JailBreakV while preserving general capabilities.
Attention dispersion during extended reasoning impairs MLLM perception on images, and a training-free VRGA framework mitigates it by selecting and reweighting visual attention heads using an entropy-focus criterion.
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.
Slower multimodal reasoning models exhibit inverse scaling in truthfulness by fabricating details under ambiguous visual inputs, while faster models remain more cautious via broader inference.
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.
A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.
citing papers explorer
-
CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs
CCTVBench exposes a large gap between standard QA accuracy and contrastive consistency in traffic video reasoning for multimodal LLMs and introduces C-TCD to narrow that gap.
-
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection
ErrorRadar is a new benchmark of 2,500 multimodal K-12 math problems for MLLM error step identification and categorization, where GPT-4o trails human experts by ~10%.
-
Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form Steering
BRACS is a barrier-regulated adaptive closed-form steering framework that reduces hallucinations in LVLMs by intervening on hidden states based on attention-measured grounding failure.
-
DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selection
A reinforcement-learned vision-language agent adaptively selects and fuses monocular depth experts per sample for better performance across camera geometries.
-
OxyEcomBench: Benchmarking Multimodal Foundation Models across E-Commerce Ecosystems
OxyEcomBench is a unified multimodal benchmark covering 6 capability areas and 29 tasks with authentic e-commerce data to measure how well foundation models handle real platform, merchant, and customer challenges.
-
Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models
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.
-
Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
GPS trains a small model on optimization history to predict prompt difficulty and select intermediate-difficulty diverse batches, yielding better training efficiency, final performance, and test-time allocation than baselines on reasoning benchmarks.
-
From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
-
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
Chain-of-Zoom factorizes extreme super-resolution into an autoregressive sequence of intermediate scales using a reused backbone model plus GRPO-tuned multi-scale VLM prompts.
-
Unified Reward Model for Multimodal Understanding and Generation
UnifiedReward is the first unified reward model that jointly assesses multimodal understanding and generation to provide better preference signals for aligning vision models via DPO.
-
Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens
Reweighting training emphasis toward image-negative tokens and filtering hallucinated data reduces object hallucination in LVLMs across three model variants.
-
Deep Pre-Alignment for VLMs
Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.
-
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.
-
CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering
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.
-
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
MiniCPM-o 4.5 uses the Omni-Flow streaming framework to deliver real-time full-duplex omni-modal interaction with proactive behavior in a 9B model that approaches Gemini 2.5 Flash performance.
-
When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs
Hallucinations in LVLMs largely arise from textual priors in prompts, and can be reduced by fine-tuning with preference optimization on grounded vs. hallucinated response pairs.
-
S2H-DPO: Hardness-Aware Preference Optimization for Vision-Language Models
S2H-DPO generates hierarchical prompt-driven preference pairs to improve multi-image reasoning in VLMs while keeping single-image performance intact.
-
Mitigating Multimodal Hallucination via Phase-wise Self-reward
PSRD mitigates visual hallucinations in LVLMs via phase-wise self-reward decoding, cutting rates by 50% on LLaVA-1.5-7B and outperforming prior methods on five benchmarks.
-
Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
DACO curates a 15,000-concept dictionary from 400K image-caption pairs and uses it to initialize an SAE that enables granular, concept-specific steering of MLLM activations, raising safety scores on MM-SafetyBench and JailBreakV while preserving general capabilities.
-
Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models
Attention dispersion during extended reasoning impairs MLLM perception on images, and a training-free VRGA framework mitigates it by selecting and reweighting visual attention heads using an entropy-focus criterion.
-
TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
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.
-
When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning
Slower multimodal reasoning models exhibit inverse scaling in truthfulness by fabricating details under ambiguous visual inputs, while faster models remain more cautious via broader inference.
-
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.
-
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
A two-stage RL framework first boosts text reasoning in 3B LMMs then adapts it to multimodal inputs, producing modest benchmark gains of 4.5-4.8%.
-
Visual-RFT: Visual Reinforcement Fine-Tuning
Visual-RFT applies reinforcement learning with verifiable perception rewards to improve large vision-language models on fine-grained classification, few-shot detection, and grounding tasks.
-
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.
-
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Mixed Preference Optimization with the MMPR dataset boosts multimodal CoT reasoning, lifting InternVL2-8B to 67.0 accuracy on MathVista (+8.7 points) and matching the 76B model.
-
Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
-
See Only When Needed: Context-Aware Attention Intervention for Mitigating Hallucinations in LVLMs
CAI is a training-free inference-time attention intervention that uses two-axis selectivity (where to look and when to intervene) via entropy- and depth-gating to mitigate hallucinations in LVLMs while preserving fluency.
-
Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation
OPPO is an evidence-aware preference optimization that contrasts faithful responses under varying visual evidence strengths to reduce hallucinations in MLLMs.
-
Generating Place-Based Compromises Between Two Points of View
Empathic similarity feedback in prompts generates more acceptable compromises than chain-of-thought, and margin-based training on the resulting data lets smaller models produce them without ongoing empathy estimation.
-
Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?
Longer textual reasoning chains degrade MLLM accuracy on fine-grained visual tasks; a new normalization and constrained-reward training framework mitigates the effect and sets new SOTA numbers.
-
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
An 8B MLLM reaches state-of-the-art efficiency and performance under 30B by combining a unified 3D resampler, joint document-text training, and hybrid RL for reasoning modes.
-
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.
-
mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration
mPLUG-Owl2 presents a modular MLLM architecture that enables modality collaboration via shared functional modules and modality-adaptive components, achieving SOTA on both text and multi-modal tasks with one generic model.
-
Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning
Vision-EKIPL injects high-quality actions from external models into RL training to expand exploration and raise the reasoning ceiling of MLLMs, reporting up to 5% gains on the Reason-RFT-CoT benchmark.
-
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.
-
Toward Native Multimodal Modeling: A Roadmap
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-based native multimodal modeling.
-
A Survey on Hallucination in Large Vision-Language Models
This survey reviews the definition, symptoms, evaluation benchmarks, root causes, and mitigation methods for hallucinations in large vision-language models.
-
A Survey on Multimodal Large Language Models
This survey organizes the architectures, training strategies, data, evaluation methods, extensions, and challenges of Multimodal Large Language Models.
- ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison
- Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models