Pith. sign in

REVIEW 12 cited by

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.00849 v2 pith:MKK64FZN submitted 2023-12-01 cs.CL cs.CV

Tianyu Yu , Yuan Yao , Haoye Zhang , Taiwen He , Yifeng Han , Ganqu Cui , Jinyi Hu , Zhiyuan Liu
show 3 more authors
Hai-Tao Zheng Maosong Sun Tat-Seng Chua
This is my paper
classification cs.CLcs.CV
keywords rlhf-vhumanmllmsdatafeedbackmllmalignmentannotated
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in multimodal understanding, reasoning, and interaction. However, existing MLLMs prevalently suffer from serious hallucination problems, generating text that is not factually grounded in associated images. The problem makes existing MLLMs untrustworthy and thus impractical in real-world (especially high-stakes) applications. To address the challenge, we present RLHF-V, which enhances MLLM trustworthiness via behavior alignment from fine-grained correctional human feedback. Specifically, RLHF-V collects human preference in the form of segment-level corrections on hallucinations, and performs dense direct preference optimization over the human feedback. Comprehensive experiments on five benchmarks in both automatic and human evaluation show that, RLHF-V can enable substantially more trustworthy MLLM behaviors with promising data and computation efficiency. Remarkably, using 1.4k annotated data samples, RLHF-V significantly reduces the hallucination rate of the base MLLM by 34.8%, outperforming the concurrent LLaVA-RLHF trained on 10k annotated data. The final model achieves state-of-the-art performance in trustworthiness among open-source MLLMs, and shows better robustness than GPT-4V in preventing hallucinations aroused from over-generalization. We open-source our code, model, and data at https://github.com/RLHF-V/RLHF-V.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Rethinking Visual Neglect: Steering via Context-Preference for MLLM Hallucination Mitigation

    cs.CL 2026-05 unverdicted novelty 7.0 of 10

    CAS mitigates object hallucinations in MLLMs by extracting two context preference vectors from designed conflict samples and applying signed residual injection at mid-early MLP layers without retraining or added latency.

  2. Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

    cs.CV 2024-06 unverdicted novelty 7.0 of 10

    Cambrian-1 is a vision-centric multimodal LLM family that evaluates over 20 vision encoders, introduces CV-Bench and the Spatial Vision Aggregator, and releases open models, code, and data achieving strong performance...

  3. Dual-Pathway Circuits of Object Hallucination in Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    Vision-language models contain identifiable grounding and hallucination pathways; suppressing the latter reduces object hallucinations by up to 76% while preserving accuracy.

  4. CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    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 ...

  5. MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

    cs.CV 2024-12 unverdicted novelty 6.0 of 10

    VPiT enables pretrained LLMs to perform both visual understanding and generation by predicting discrete text tokens and continuous visual tokens, with understanding data proving more effective than generation-specific data.

  6. CAST: Mitigating Object Hallucination in Large Vision-Language Models via Caption-Guided Visual Attention Steering

    cs.CV 2026-05 conditional novelty 5.0 of 10

    A training-free method that steers specific attention heads toward caption-query states reduces object hallucination in LVLMs by ~6% on average across five benchmarks.

  7. Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs

    cs.CV 2026-02 conditional novelty 5.0 of 10

    Visual token compression (4x fewer tokens) plus a three-stage generative/contrastive/judge-curated training pipeline yields state-of-the-art MLLM-based retrieval accuracy at lower inference cost.

  8. Hallucination of Multimodal Large Language Models: A Survey

    cs.CV 2024-04 accept novelty 5.0 of 10

    The survey organizes causes of hallucinations in MLLMs, reviews evaluation benchmarks and metrics, and outlines mitigation approaches plus open questions.

  9. Aligning Modalities in Vision Large Language Models via Preference Fine-tuning

    cs.LG 2024-02 unverdicted novelty 5.0 of 10

    POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.

  10. Toward Native Multimodal Modeling: A Roadmap

    cs.CV 2026-05 unverdicted novelty 3.0 of 10

    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-...

  11. A Survey on Hallucination in Large Vision-Language Models

    cs.CV 2024-02 unverdicted novelty 3.0 of 10

    This survey reviews the definition, symptoms, evaluation benchmarks, root causes, and mitigation methods for hallucinations in large vision-language models.

  12. A Survey on Multimodal Large Language Models

    cs.CV 2023-06 accept novelty 3.0 of 10

    This survey organizes the architectures, training strategies, data, evaluation methods, extensions, and challenges of Multimodal Large Language Models.

Pith tools