The proliferation of large-scale AI models trained on extensive datasets has
revolutionized machine learning. With these models taking on increasingly
central roles in various applications, the need to understand their behavior
and enhance interpretability has become paramount. To investigate the impact of
changes in training data on a pre-trained model, a common approach is
leave-one-out retraining. This entails systematically altering the training
dataset by removing specific samples to observe resulting changes within the
model. However, retraining the model for each altered dataset presents a
significant computational challenge, given the need to perform this operation
for every dataset variation. In this paper, we introduce an efficient framework
for assessing data impact, comprising offline training and online evaluation
stages. During the offline training phase, we approximate the influence of
training data on the target model through a distilled synset, formulated as a
reversed gradient matching problem. For online evaluation, we expedite the
leave-one-out process using the synset, which is then utilized to compute the
attribution matrix based on the evaluation objective. Experimental evaluations,
including training data attribution and assessments of data quality,
demonstrate that our proposed method achieves comparable model behavior
evaluation while significantly speeding up the process compared to the direct
retraining method.

通过在线和离线阶段，我们提出了一种高效的框架，评估训练数据对目标模型的影响，通过反向梯度匹配问题建立了一个精简同义词集，用于加速离开一个样本的过程，并计算评估目标基于的归因矩阵。实验证明，相比直接重新训练方法，我们的方法在实现了可比较的模型行为评估的同时，显著加快了过程。

逆梯度匹配的精简数据模型

Distilled Datamodel with Reverse Gradient Matching

The complexity of psychological principles underscore a significant societal
challenge, given the vast social implications of psychological problems.
Bridging the gap between understanding these principles and their actual
clinical and real-world applications demands rigorous exploration and adept
implementation. In recent times, the swift advancement of highly adaptive and
reusable artificial intelligence (AI) models has emerged as a promising way to
unlock unprecedented capabilities in the realm of psychology. This paper
emphasizes the importance of performance validation for these large-scale AI
models, emphasizing the need to offer a comprehensive assessment of their
verification from diverse perspectives. Moreover, we review the cutting-edge
advancements and practical implementations of these expansive models in
psychology, highlighting pivotal work spanning areas such as social media
analytics, clinical nursing insights, vigilant community monitoring, and the
nuanced exploration of psychological theories. Based on our review, we project
an acceleration in the progress of psychological fields, driven by these
large-scale AI models. These future generalist AI models harbor the potential
to substantially curtail labor costs and alleviate social stress. However, this
forward momentum will not be without its set of challenges, especially when
considering the paradigm changes and upgrades required for medical
instrumentation and related applications.

心理学中的复杂原理与广泛社会影响形成了一个重要的社会挑战。近年来，高度适应和可复用的人工智能模型在心理学领域崛起，强调了对这些大规模人工智能模型的性能验证的重要性，同时突出了这些模型在社交媒体分析、临床护理洞察、社区监测和心理学理论的细致探索等领域的前沿进展和实际应用。基于我们的综述，我们预示心理学领域将会加速发展，这源于这些大规模人工智能模型的推动。这些未来的综合型人工智能模型有望大幅降低劳动成本并缓解社会压力，然而，这种前进的势头在考虑到医疗仪器和相关应用所需的范式变革和升级时也面临一系列挑战。