Papers › RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained...

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

1 Dec 2023CVPR 2024 1arXiv:2312.00849archive 2025-07-28

Tianyu Yu, Yuan YAO, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, Tat-Seng Chua

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.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

rlhf-v/rlhf-v officialmentioned in papermentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness (arXiv:2405.17220; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 3 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
exgc/r1v-free mentioned on GitHubpytorchSyntology: not harvested report
openbmb/minicpm-v mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MiniCPM-V: A GPT-4V Level MLLM on Your Phone (arXiv:2408.01800; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
tidedra/vl-rlhf mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ACL Anthology id 2025.naacl-long.447 (that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

HallucinationImage CaptioningVisual Question Answering

Datasets

Introduced by this paper, per the archive.

RLHF-V Dataset

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Captioning Object HalBench RLHF-V chair_i 7.5 #1 of 3 Archive leaderboard report
Image Captioning Object HalBench RLHF-V chair_s 12.2 #1 of 3 Archive leaderboard report
Visual Question Answering VQA v2 RLHF-V Accuracy 80 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

BASE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections