The Shared Latent Structure of LLM Psychometric Responses

arXiv:2605.05080 · cs.CL · Submitted 2026-05-06 · Read on arXiv

cs.CL

Submitted: 2026-05-06

Updated: 2026-10-13

Code: https://github.com/hplisiecki/Pinocchio

Terminology

• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• Understanding intermediate layers using linear classifier probes
• Tell me about yourself: LLMs are aware of their learned behaviors
• Looking Inward: Language Models Can Learn About Themselves by Introspection
• Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
• A New Pair of GloVes
• Could a Large Language Model be Conscious?
• Does It Make Sense to Speak of Introspection in Large Language Models?
• A Detailed Factor Analysis for the Political Compass Test: Navigating Ideologies of Large Language Models
• On the Credibility of Evaluating LLMs using Survey Questions
• From Prompts to Constructs: A Dual-Validity Framework for LLM Research in Psychology
• The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
• Who is GPT-3? An Exploration of Personality, Values and Demographics
• Scikit-learn: Machine Learning in Python
• Interpretable Semantic Gradients in SSD: A PCA Sweep Approach and a Case Study on AI Discourse
• Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias
• Large Language Models Show Human-like Social Desirability Biases in Survey Responses
• Challenging the Validity of Personality Tests for Large Language Models
• Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Models
• Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering