缓解低级视觉幻觉需要自我意识：数据库、模型与训练策略
Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model and Training Strategy
AI总结：
针对多模态大模型在低级视觉任务中的幻觉问题，提出HLPU数据库、SAFEQA模型和ESA-PO训练框架，通过增强模型自我意识显著减少幻觉并提升性能。
摘要：
多模态大语言模型的快速发展带来了视觉感知与理解方面的显著进步，将多个任务整合到一个统一的视觉问答框架中。然而，这些模型容易产生幻觉，这限制了它们作为人工智能系统的可靠性。虽然这一问题在自然语言处理和图像描述中已得到广泛研究，但在低级视觉感知与理解（HLPU）中的幻觉研究仍然缺乏，尤其是在图像质量评估任务的背景下。我们认为这些幻觉源于模型内部缺乏清晰的自我意识。为解决这一问题，我们首先引入了HLPU指令数据库，这是首个专门针对低级视觉任务中幻觉的指令数据库。该数据库包含约20万个问答对，由四个子集组成，每个子集涵盖不同类型的指令。随后，我们提出了自我意识失败消除（SAFEQA）模型，该模型利用图像特征、显著区域特征和质量特征来提升模型在低级视觉任务中的感知与理解能力。此外，我们提出了增强自我意识偏好优化（ESA-PO）框架，以增强模型对知识边界的意识，从而减少幻觉的发生。最后，我们在低级视觉任务上进行了全面实验，结果表明我们提出的方法显著增强了模型在这些任务中的自我意识并减少了幻觉。值得注意的是，我们提出的方法提高了所提模型的准确性和自我意识，并在多种评估指标上优于闭源模型。
英文摘要：
The rapid development of multimodal large language models has resulted in remarkable advancements in visual perception and understanding, consolidating several tasks into a single visual question-answering framework. However, these models are prone to hallucinations, which limit their reliability as artificial intelligence systems. While this issue is extensively researched in natural language processing and image captioning, there remains a lack of investigation of hallucinations in Low-level Visual Perception and Understanding (HLPU), especially in the context of image quality assessment tasks. We consider that these hallucinations arise from an absence of clear self-awareness within the models. To address this issue, we first introduce the HLPU instruction database, the first instruction database specifically focused on hallucinations in low-level vision tasks. This database contains approximately 200K question-answer pairs and comprises four subsets, each covering different types of instructions. Subsequently, we propose the Self-Awareness Failure Elimination (SAFEQA) model, which utilizes image features, salient region features and quality features to improve the perception and comprehension abilities of the model in low-level vision tasks. Furthermore, we propose the Enhancing Self-Awareness Preference Optimization (ESA-PO) framework to increase the model's awareness of knowledge boundaries, thereby mitigating the incidence of hallucination. Finally, we conduct comprehensive experiments on low-level vision tasks, with the results demonstrating that our proposed method significantly enhances self-awareness of the model in these tasks and reduces hallucinations. Notably, our proposed method improves both accuracy and self-awareness of the proposed model and outperforms close-source models in terms of various evaluation metrics.
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。
