用脑信号监督让大模型学会人类抽象思维，提升理解力与泛化能力。
Human-like Cognitive Generalization for Large Models via Brain-in-the-loop Supervision
- 通过少量脑信号引导模型学习人类概念结构
- 在少样本和分布外任务上性能显著提升
- 适合研究具身智能与可解释人工智能的学者
近年来，深度神经网络（尤其是大规模语言模型）在图像和自然语言理解方面表现出色。尽管随着训练数据量增加而扩大模型参数能持续提升性能，但实现理解抽象概念、推理和适应新场景等人类认知的复杂能力仍是重大挑战。本研究发现，利用少量脑信号进行‘脑中回路’监督学习，可有效将人类概念结构迁移至深度神经网络，显著增强其对抽象乃至未见过概念的理解能力。实验结果表明，这种增强的认知能力带来了在少样本/零样本学习和分布外识别等困难任务上的显著性能提升，同时生成高度可解释的概念表示。研究显示，人机协同监督能有效增强大模型的复杂认知能力，为构建更类人的智能系统提供了可行路径。
原文摘要 · Abstract (English)
Recent advancements in deep neural networks (DNNs), particularly large-scale language models, have demonstrated remarkable capabilities in image and natural language understanding. Although scaling up model parameters with increasing volume of training data has progressively improved DNN capabilities, achieving complex cognitive abilities - such as understanding abstract concepts, reasoning, and adapting to novel scenarios, which are intrinsic to human cognition - remains a major challenge. In this study, we show that brain-in-the-loop supervised learning, utilizing a small set of brain signals, can effectively transfer human conceptual structures to DNNs, significantly enhancing their comprehension of abstract and even unseen concepts. Experimental results further indicate that the enhanced cognitive capabilities lead to substantial performance gains in challenging tasks, including few-shot/zero-shot learning and out-of-distribution recognition, while also yielding highly interpretable concept representations. These findings highlight that human-in-the-loop supervision can effectively augment the complex cognitive abilities of large models, offering a promising pathway toward developing more human-like cognitive abilities in artificial systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。