提升LVLM中对齐的偏差自评判方法
Improving Alignment in LVLMs with Debiased Self-Judgment
AI总结：
本文提出一种基于模型内部生成的去偏自评判分数的方法，使LVLM无需外部资源即可自主改进对齐，减少幻觉并提升安全性和整体能力。
摘要：
大型语言模型（LLMs）和大型视觉-语言模型（LVLMs）的快速发展为整合视觉和语言模态带来了新的机遇。然而，有效对齐这些模态仍然具有挑战性，常常导致幻觉——即生成的输出不基于视觉输入——并在各个领域引发安全问题。现有的对齐方法，如指令微调和偏好微调，往往依赖外部数据集、人工标注或复杂的后处理，这限制了可扩展性并增加了成本。为应对这些挑战，我们提出了一种新方法，生成去偏自评判分数（debiased self-judgment score），这是一种由模型内部创建、不依赖外部资源的自我评估指标。这使得模型能够自主改进对齐。我们的方法增强了解码策略和偏好微调过程，从而减少了幻觉，增强了安全性，并提升了整体能力。实证结果表明，我们的方法显著优于传统方法，为对齐LVLMs提供了一种更有效的解决方案。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
