对症下药：通过针对性指令调优缓解大型视觉语言模型中的幻觉问题
Prescribing the Right Remedy: Mitigating Hallucinations in Large Vision-Language Models via Targeted Instruction Tuning
AI总结：
本文提出针对性指令数据生成框架DFTG，通过幻觉诊断和针对性数据生成两个阶段，针对不同大型视觉语言模型的幻觉特异性定制训练数据，实验证明其缓解幻觉的效果优于现有数据集。
摘要：
尽管当前的大型视觉语言模型（LVLMs）在各种跨模态任务上取得了优异表现，但它们仍然存在幻觉问题，表现为生成的回答与对应图像之间的不一致。先前的研究指出，指令数据的低质量，尤其是正负样本之间的不平衡，是导致模型幻觉的重要因素。最近，研究者提出了高质量的指令数据集，如LRV-Instruction，以缓解模型幻觉。然而，我们的调查发现，不同LVLMs的幻觉概念表现出特异性，即幻觉概念的分布在不同模型之间存在显著差异。现有数据集在设计过程中未考虑不同模型的幻觉特异性，从而削弱了它们缓解模型幻觉的效果。在本文中，我们提出了一个名为DFTG的针对性指令数据生成框架，该框架针对不同模型的幻觉特异性进行定制。具体而言，DFTG包含两个阶段：幻觉诊断，从模型的回答和图像中提取必要信息以进行幻觉诊断；以及针对性数据生成，根据诊断结果生成针对性指令数据。在幻觉基准上的实验结果表明，与先前数据集相比，我们的方法生成的针对性指令数据在缓解幻觉方面更为有效。
英文摘要：
Despite achieving outstanding performance on various cross-modal tasks, current large vision-language models (LVLMs) still suffer from hallucination issues, manifesting as inconsistencies between their generated responses and the corresponding images. Prior research has implicated that the low quality of instruction data, particularly the skewed balance between positive and negative samples, is a significant contributor to model hallucinations. Recently, researchers have proposed high-quality instruction datasets, such as LRV-Instruction, to mitigate model hallucination. Nonetheless, our investigation reveals that hallucinatory concepts from different LVLMs exhibit specificity, i.e. the distribution of hallucinatory concepts varies significantly across models. Existing datasets did not consider the hallucination specificity of different models in the design processes, thereby diminishing their efficacy in mitigating model hallucination. In this paper, we propose a targeted instruction data generation framework named DFTG that tailored to the hallucination specificity of different models. Concretely, DFTG consists of two stages: hallucination diagnosis, which extracts the necessary information from the model's responses and images for hallucination diagnosis; and targeted data generation, which generates targeted instruction data based on diagnostic results. The experimental results on hallucination benchmarks demonstrate that the targeted instruction data generated by our method are more effective in mitigating hallucinations compared to previous datasets.
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。
