Score: 1

Improving Alignment in LVLMs with Debiased Self-Judgment

Published: August 28, 2025 | arXiv ID: 2508.20655v2

By: Sihan Yang , Chenhang Cui , Zihao Zhao and more

Potential Business Impact:

Model judges its own answers to be safer.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

The rapid advancements in Large Language Models (LLMs) and Large Visual-Language Models (LVLMs) have opened up new opportunities for integrating visual and linguistic modalities. However, effectively aligning these modalities remains challenging, often leading to hallucinations--where generated outputs are not grounded in the visual input--and raising safety concerns across various domains. Existing alignment methods, such as instruction tuning and preference tuning, often rely on external datasets, human annotations, or complex post-processing, which limit scalability and increase costs. To address these challenges, we propose a novel approach that generates the debiased self-judgment score, a self-evaluation metric created internally by the model without relying on external resources. This enables the model to autonomously improve alignment. Our method enhances both decoding strategies and preference tuning processes, resulting in reduced hallucinations, enhanced safety, and improved overall capability. Empirical results show that our approach significantly outperforms traditional methods, offering a more effective solution for aligning LVLMs.

Country of Origin
🇺🇸 United States

Repos / Data Links

Page Count
20 pages

Category
Computer Science:
CV and Pattern Recognition