arXiv cs.AI· Ziquan Zhu, Hanruo Zhu, Si-Yuan Lu, Morris Yu-Chao Huang, Yicheng Lin, Wei Han, Tianlong Chen, Mingyuan Wu, Hanchao Yu, Gaojie Jin, Lu Liu, Bo Sun, Tianjin Huang·· 4 小时前AI 评分18
MOTIVE:视觉语言模型多视角自验证框架论文被作者撤回
When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models
AI 导读
arXiv 论文 2610.07018 提出的 MOTIVE 框架从多视角评估候选答案,通过正确性对齐的可靠性分数决定接受或重思,在多模态基准和多种 VLM 骨干上优于自验证与自纠错基线。该预印本已由作者撤回,原因是获得新实验结果,正大幅重写稿件,暂无替换版本。
正文 · 原文
This paper has been withdrawn by Ziquan Zhu
Authors:Ziquan Zhu, Hanruo Zhu, Si-Yuan Lu, Morris Yu-Chao Huang, Yicheng Lin, Wei Han, Tianlong Chen, Mingyuan Wu, Hanchao Yu, Gaojie Jin, Lu Liu, Bo Sun, Tianjin Huang
No PDF available, click to view other formats
Abstract:Vision-language models (VLMs) have achieved strong performance in multimodal reasoning, yet they remain prone to generating plausible but incorrect answers. Self-verification offers a practical way to improve answer reliability without relying on external judges, but existing methods typically depend on a single verification criterion or fixed prompt, resulting in incomplete and unstable reliability estimates. We first systematically analyze how verifier capability and prompt design affect verification performance. Our findings show that stronger verifiers provide more reliable judgments, while verification performance is highly sensitive to prompt choice, with no single prompt consistently dominating across tasks. Guided by these findings, we propose \texttt{MOTIVE}, a \textbf{M}ulti-View Self-Verificati\textbf{O}n wi\textbf{T}h Rel\textbf{I}ability-Guided Selecti\textbf{VE} Rethinking framework for reliable multimodal reasoning. \texttt{MOTIVE} evaluates each candidate answer from complementary verification perspectives and learns a correctness-aligned reliability score through correctness-grounded multi-view verification learning. During inference, this score governs an accept-or-rethink decision, allowing reliable answers to be returned directly while uncertain ones trigger history-guided rethinking. Extensive experiments across diverse multimodal benchmarks and VLM backbones demonstrate that \texttt{MOTIVE} consistently outperforms strong self-verification and self-correction baselines. Further results show that reliable verification improves accept-or-rethink decisions and reduces unnecessary reasoning turns, enabling more reliable and efficient self-verification without an external judge.
| Comments: | The authors request withdrawal of this preprint. We have obtained additional experimental results and are substantially rewriting the manuscript to incorporate these findings and expand the analysis. No replacement version is currently available |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.07018 [cs.AI] |
| (or arXiv:2610.07018v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07018 arXiv-issued DOI via DataCite |
Submission history
From: Ziquan Zhu [view email]
[v1]
Sun, 4 Oct 2026 15:08:07 UTC (9,818 KB)
[v2]
Fri, 13 Nov 2026 12:17:39 UTC (1 KB) (withdrawn)
来源:arXiv cs.AI · arxiv.org