Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Stereotype Content Model02:16

Stereotype Content Model

The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence categorization, a person will feel...
Language and Cognition01:27

Language and Cognition

Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
Modeling in Therapy01:26

Modeling in Therapy

Modeling, a key technique in therapy, uses observational learning to help clients acquire and practice new skills by watching therapists demonstrate desired behaviors. This approach, rooted in Albert Bandura's concept of vicarious learning, plays a significant role in therapeutic interventions for various psychological conditions, including social anxiety, ADHD, and depression.
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in situations...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Artificial platelets suppressing deep vein thrombosis via competitive adhesion.

Bioactive materials·2026
Same author

Towards the construction of a virtual yeast.

Nature·2026
Same author

Inflammation Impairs Poststroke Recovery by Disrupting Iron Homeostasis in Brain.

Antioxidants & redox signaling·2026
Same author

Structure-Informed Design of Distinct Parallel G-Quadruplex Stabilizers for KRAS-Driven Cancer Therapy.

Angewandte Chemie (International ed. in English)·2026
Same author

Genomic epidemiology reveals the origins and transmission dynamics of chikungunya virus in China.

Infectious diseases of poverty·2026

Related Experiment Video

Updated: Jul 12, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Symbolic Preference Distillation: Advancing Small Language Models for Mental Health Analysis.

Lu Yu, Wei Xiang, Kang Han

    IEEE Journal of Biomedical and Health Informatics
    |July 9, 2026
    PubMed
    Summary
    This summary is machine-generated.

    Symbolic preference distillation (SyPD) enhances small language models (SLMs) for mental health analysis. This method improves SLM reasoning, achieving high accuracy in mental disorder diagnosis with fewer parameters.

    Related Experiment Videos

    Last Updated: Jul 12, 2026

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
    03:14

    Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

    Published on: December 6, 2024

    Area of Science:

    • Artificial Intelligence
    • Computational Linguistics
    • Clinical Psychology

    Background:

    • Large language models (LLMs) show promise in mental health analysis but are computationally expensive.
    • Small language models (SLMs) struggle with complex reasoning and domain-specific knowledge required for clinical tasks.

    Purpose of the Study:

    • To enhance the complex reasoning abilities of SLMs for mental health analysis tasks.
    • To develop a method that overcomes the limitations of SLMs in capturing general cognitive abilities and specialized domain knowledge.

    Main Methods:

    • Proposed symbolic preference distillation (SyPD) for SLMs.
    • Implemented a reasoning optimization strategy using specialized domain knowledge for error analysis and symbolic knowledge generation.
    • Utilized a preference distillation method guiding SLMs with high-quality reasoning from a teacher LLM via preference signals and symbolic knowledge.

    Main Results:

    • SyPD, with 1.1 billion parameters, achieved an average weighted F1-score of 0.815 on mental disorder diagnosis.
    • Outperformed MentaLLaMA-Chat-13B by 6.14% and GPT-4 by 15.44% on the IMHI benchmark.
    • Demonstrated effective post-hoc correction of failure cases and acquisition of domain-specific knowledge.

    Conclusions:

    • SyPD significantly improves SLM performance in mental health analysis, making advanced AI more accessible for clinical applications.
    • The proposed method offers a computationally efficient alternative to large models without sacrificing accuracy in complex reasoning tasks.