医学-VCD:通过视觉对比解码缓解医疗大视觉语言模型的幻觉
Zahra Mahdavi1, Zahra Khodakaramimaghsoud2, Hooman Khaloo3
1Department of computer science , University of Central Florida, Orlando, USA.
Computers in biology and medicine
|November 30, 2025
概括
医疗保健中的大型视觉语言模型 (LVLM) 可以产生幻觉. Med-VCD是一种新的解码方法,通过专注于视觉证据而不会减缓模型,从而减少这些错误.
科学领域:
- 人工智能的人工智能
- 医疗成像医学成像
- 自然语言处理自然语言处理.
背景情况:
- 大视觉语言模型 (LVLMs) 在医疗保健中越来越多地用于医疗视觉问题回答和报告生成等任务.
- 对LVLMs的一个重大挑战是他们倾向于产生可能但事实上不正确的幻觉输出.
- 现有的减少幻觉的方法通常涉及缓慢的二次解码或特定领域的方法,这些方法可能会导致错位.
研究的目的:
- 引入Med-VCD,一种新的稀疏视觉对比解码方法,旨在减轻医疗LVLM中的幻觉.
- 解决现有的幻觉缓解策略的局限性,特别是它们对推断速度和域特异性的影响.
- 提高医疗LVLM的可靠性和事实准确性,而不会影响效率.
主要方法:
- Med-VCD采用一种稀疏的视觉对比解码方法.
- 它使用了一种新的令牌分散策略,以动态选择视觉相关的令牌.
- 这种方法减少了冗余性,同时保持了基本的视觉上下文,提高了效率和可靠性.
主要成果:
- 在医疗 LVLM 中,Med-VCD 显著减少了幻觉.
- 在八个不同的医疗数据集 (眼科,放射学,病理学) 中进行的评估表明有所改善.
- 与基线模型相比,事实准确度平均增加了13%,幻觉准确度提高了6%.
结论:
- Med-VCD提供了一种有效和高效的解决方案,以减轻医疗LVLM中的幻觉.
- 该方法提高了事实准确性和可靠性,而不需要传统二次解码技术的计算开销.
- Med-VCD代表了可信的人工智能应用在医疗成像中的有希望的进步.
相关概念视频
01:12Visual Agnosia
899
Visual agnosia is a condition characterized by the inability to recognize visually presented objects despite having normal vision. For instance, a person with visual agnosia can describe the shape and color of an object but cannot identify or name it. This impairment does not affect their visual field, acuity, color vision, brightness discrimination, language, or memory. An example of this condition in a social setting is someone at a dinner party asking for "that silver thing with a round...
899
01:24Prosopagnosia
668
Prosopagnosia, also known as face blindness, is the inability to recognize faces. In severe cases, individuals with prosopagnosia may not recognize close family members, including parents and spouses, by their faces. For instance, someone with prosopagnosia might walk past their child in a crowd, only realizing their mistake upon noticing their child's distinctive backpack or favorite jacket. Prosopagnosia specifically impairs facial recognition, while the recognition of other objects or...
668
01:24Color Vision
1.3K
Color perception begins in the retina, the light-sensitive layer at the back of the eye. Two main theories explain how colors are seen: the trichromatic theory and the opponent-process theory. The trichromatic theory, proposed by Thomas Young in 1802 and extended by Hermann von Helmholtz in 1852, suggests that color vision is based on three types of cone receptors in the retina. These cones are sensitive to different but overlapping ranges of wavelengths corresponding to red, blue, and green.
1.3K