FROMANNUAL REVIEWS

CogSci 2025

•

August 01, 2025

•

San Francisco, United States

keywords:

psychology

artificial intelligence

natural language processing

Large language models (LLMs) excel at personality prediction but are often impractical for deployment due to high computational demands. This work introduces cognitive distillation with Chain-of-Thought calibration, a novel framework for transferring structured reasoning from large LLMs to smaller, efficient models. Inspired by cognitive architectures like ACT-R, our method aligns intermediate inference steps using exemplars from single or multiple LLMs. A 1.5B-parameter model distilled through this process surpasses Qwen1.5-110B in predictive accuracy, achieving a 28% improvement in Pearson correlation while using just 1.36% of its parameters. Ablation studies reveal that moderate sampling diversity and multi-model ensembles enhance cognitive skill transfer and construct validity. These findings demonstrate that high-level reasoning can be efficiently and faithfully transferred, enabling psychometrically robust personality assessment in resource-constrained settings. This approach bridges AI and cognitive science, offering a scalable path toward plausible, cognitively grounded language models.

Downloads

PaperTranscript English (automatic)

Next from CogSci 2025

Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play
poster

Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play

CogSci 2025

Yifan Zeng and 2 other authors

01 August 2025

Similar lecture

Cognitive Representation in Large Language Models: Formalizing Psychological Constructs for Automated Questionnaire Generation
poster

Cognitive Representation in Large Language Models: Formalizing Psychological Constructs for Automated Questionnaire Generation

CogSci 2025

Yang Yan
Zhenzhong Lan
+2
Yang Yan and 4 other authors

01 August 2025

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Presentations
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2026 Underline - All rights reserved

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.