Embracing naturalistic paradigms: substituting GPT predictions for human judgments
Yang, X.; O'Reilly, C.; Shinkareva, S. V.
Show abstract
Naturalistic paradigms can assure ecological validity and yield novel insights in psychology and neuroscience. However, using behavioral experiments to obtain the human ratings necessary to analyze data collected with these paradigms is usually costly and time-consuming. Large language models like GPT have great potential for predicting human-like behavioral judgments. The current study evaluates the performance of GPT as a substitute for human judgments for affective dynamics in narratives. Our results revealed that GPTs inference of hedonic valence dynamics is highly correlated with human affective perception. Moreover, the inferred neural activity based on GPT-derived valence ratings is similar to inferred neural activity based on human judgments, suggesting the potential of using GPTs prediction as a reliable substitute for human judgments.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- NeuroConText: Contrastive Learning for Neuroscience Meta-Analysis with Rich Text Representation 94%
- Methods for decoding cortical gradients of functional connectivity 93%
- Alignment massive of auditory individual artificial networks with fMRI brain data leads to generalizable improvements in brain encoding and downstream tasks 92%
Similar papers in this journal
Similar papers in this journal
- Meta-Analysis of the Functional Neuroimaging Literature with Probabilistic Logic Programming 93%
- Predicting the subjective intensity of imagined sensory experiences from electrophysiological measures of oscillatory brain activity. 93%
- Longitudinal Changes in Auditory and Reward Systems Following Receptive Music-Based Intervention in Older Adults 92%
Similar papers in this journal
- Deep Multimodal Representations and Classification of First-Episode Psychosis via Live Face Processing 93%
- Music as a real-time fMRI neurofeedback interface for modulating interhemispheric connectivity: effects on mood and recruitment of the putamen and insula 92%
- Common Data Elements, Scalable Data Management Infrastructure and Analytics Workflows for Large-scale Neuroimaging Studies 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.