Paper List
-
Nyxus: A Next Generation Image Feature Extraction Library for the Big Data and AI Era
This paper addresses the core pain point of efficiently extracting standardized, comparable features from massive (terabyte to petabyte-scale) biomedi...
-
Topological Enhancement of Protein Kinetic Stability
This work addresses the long-standing puzzle of why knotted proteins exist by demonstrating that deep knots provide a functional advantage through enh...
-
A Multi-Label Temporal Convolutional Framework for Transcription Factor Binding Characterization
This paper addresses the critical limitation of existing TF binding prediction methods that treat transcription factors as independent entities, faili...
-
Social Distancing Equilibria in Games under Conventional SI Dynamics
This paper solves the core problem of proving the existence and uniqueness of Nash equilibria in finite-duration SI epidemic games, showing they are a...
-
Binding Free Energies without Alchemy
This paper addresses the core bottleneck of computational expense in Absolute Binding Free Energy calculations by eliminating the need for numerous al...
-
SHREC: A Spectral Embedding-Based Approach for Ab-Initio Reconstruction of Helical Molecules
This paper addresses the core bottleneck in cryo-EM helical reconstruction: eliminating the dependency on accurate initial symmetry parameter estimati...
-
Budget-Sensitive Discovery Scoring: A Formally Verified Framework for Evaluating AI-Guided Scientific Selection
This paper addresses the critical gap in evaluating AI-guided scientific selection strategies under realistic budget constraints, where existing metri...
-
Probabilistic Joint and Individual Variation Explained (ProJIVE) for Data Integration
This paper addresses the core challenge of accurately decomposing shared (joint) and dataset-specific (individual) sources of variation in multi-modal...
Developing the PsyCogMetrics™ AI Lab to Evaluate Large Language Models and Advance Cognitive Science
Marywood University | The University of Scranton | University of North Carolina Wilmington | California State University Dominguez Hills
30秒速读
IN SHORT: This paper addresses the critical gap between sophisticated LLM evaluation needs and the lack of accessible, scientifically rigorous platforms that integrate psychometric and cognitive science methodologies for non-technical stakeholders.
核心创新
- Methodology Introduces the first cloud-based platform applying Classical Test Theory (CTT) and psychometric validity principles (Cronbach's α > .70, AVE > .50) to systematically evaluate LLMs as cognitive entities rather than mere tools.
- Methodology Implements a three-cycle Action Design Science framework (Relevance-Rigor-Design) with nested Build–Intervene–Evaluate loops, bridging Popperian falsifiability, Cognitive Load Theory, and stakeholder requirements into a unified evaluation system.
- Biology Validates that modern LLMs (GPT-4, LLaMA-3) satisfy core psychometric validity criteria—including convergent, discriminant, predictive, and external validity—and outperform earlier models (GPT-3.5, LLaMA-2) across these dimensions.
主要结论
- The PsyCogMetrics™ AI Lab successfully operationalizes psychometric principles with demonstrated reliability metrics (Cronbach's α > .70) and validity frameworks (convergent/discriminant validity) for LLM evaluation.
- The platform addresses three critical pain points: mitigates benchmark saturation through dynamic evaluation, reduces data contamination via reproducible workflows, and expands coverage through cognitive science methodologies.
- Design validation shows GPT-4 and LLaMA-3 satisfy psychometric validity criteria and outperform earlier models, with GPT-4 reaching six-year-old human parity on Theory of Mind vignettes (Strachan et al., 2024).
摘要: This study presents the development of the PsyCogMetrics™ AI Lab (https://psycogmetrics.ai), an integrated, cloud-based platform that operationalizes psychometric and cognitive-science methodologies for Large Language Model (LLM) evaluation. Framed as a three-cycle Action Design Science study, the Relevance Cycle identifies key limitations in current evaluation methods and unfulfilled stakeholder needs. The Rigor Cycle draws on kernel theories such as Popperian falsifiability, Classical Test Theory, and Cognitive Load Theory to derive deductive design objectives. The Design Cycle operationalizes these objectives through nested Build–Intervene–Evaluate loops. The study contributes a novel IT artifact, a validated design for LLM evaluation, benefiting research at the intersection of AI, psychology, cognitive science, and the social and behavioral sciences.