Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Reasoning

Reasoning

Reasoning is the action of thinking about something in a logical, sensible way. It is integral to problem-solving, decision-making, and critical thinking. Reasoning can be inductive or deductive. Reasoning involves transforming information into conclusions, which is essential for problem-solving, decision-making, and critical thinking.
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...

Language and Cognition

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.

Language Development

Language Development

Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...

Typical Model Studies

Typical Model Studies

Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.

Reason and Intuition

Reason and Intuition

The human brain processes information for decision-making using one of two routes: an intuitive system and a rational system (Epstein, 1994; popularized by Kahneman, 2011 as System 1 and System 2, respectively). The intuitive system is quick, impulsive, and operates with minimal effort, relying on emotions or habits to provide cues for what to do next, while the rational system is logical, analytical, deliberate, and methodical. Research in neuropsychology suggests that the...

You might also read

Related Articles

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

Sort by

Same author

Evaluating the effect of a school-based material needs intervention on child maltreatment investigations in Michigan: A staggered interrupted time series study.

Child abuse & neglect·2026

Same author

Validation of a Small Language Model for DSM-5 Substance Category Classification in Child Welfare Records.

Journal of evidence-based social work (2019)·2026

Same author

A school-based material needs intervention for chronic absenteeism: a state-wide staggered interrupted time series analysis.

Journal of epidemiology and community health·2025

Same author

Case reports unlocked: Leveraging retrieval-augmented generation with large language models to advance research on psychological child maltreatment.

Child abuse & neglect·2025

Same author

Clinical Social Workers' Perceptions of Large Language Models in Practice: Resistance to Automation and Prospects for Integration.

Journal of evidence-based social work (2019)·2025

Same author

Infant Toddler Court Teams, Reunification, Time to Permanency, and Placement Stability: Evidence From a Study Using Matched Controls.

Child maltreatment·2025

Search research articles

Related Experiment Video

Updated: Jan 19, 2026

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

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

Published on: December 6, 2024

Small Models Achieve Large Language Model Performance: Evaluating Reasoning-Enabled AI for Secure Child Welfare

Zia Qi¹, Brian E Perron¹, Bryan G Victor^2,3

¹School of Social Work, University of Michigan, Ann Arbor, MI, USA.

Journal of Evidence-Based Social Work (2019)

|January 18, 2026

Summary

Smaller language models with extended reasoning are more effective for identifying child welfare risks than larger models. This approach offers significant computational and time efficiencies for social work research.

Keywords:

Generative artificial intelligence benchmark development child welfare large language models model evaluation small language models

More Related Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Related Experiment Videos

Last Updated: Jan 19, 2026

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

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

Published on: December 6, 2024

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Area of Science:

Artificial Intelligence
Natural Language Processing
Social Work Research

Background:

Child welfare systems generate vast amounts of data requiring efficient analysis.
Identifying critical risk factors in child welfare records is crucial for timely intervention.
Previous research often assumed larger language models yield superior performance.

Purpose of the Study:

To develop and apply a systematic benchmarking framework for evaluating language models in child welfare record analysis.
To assess the performance of various language model sizes and architectures in identifying key risk factors.
To compare model performance across validated benchmarks for domestic violence, firearms, substance-related problems, and opioids.

Main Methods:

Construction of four distinct benchmarks (500 cases each) for domestic violence, substance-related problems, firearms, and opioids.
Evaluation of seven language model sizes (0.6B-32B parameters) using standard and extended reasoning modes.
Measurement of inter-rater reliability using Cohen's kappa to compare model classifications against human expert gold standards.

Main Results:

A 4B parameter model with extended reasoning outperformed larger models, achieving substantial to almost perfect agreement.
The small model demonstrated high accuracy (κ=0.93-0.96) on substance-related problems, firearms, and opioids benchmarks.
"Substantial" agreement (κ=0.74) was achieved on the complex domestic violence benchmark, indicating strong performance across all categories.

Conclusions:

Smaller, reasoning-enabled language models can achieve high accuracy comparable to much larger architectures.
This approach offers significant computational and time efficiencies, making advanced AI more accessible for social work research.
The developed benchmarking framework supports evidence-based model selection, balancing accuracy with resource constraints for practical deployment.