Taming the Centaur(s) with LAPITHS: a framework for a theoretically grounded interpretation of AI performances
cs.AI
Submitted: 2026-04-30
Updated: 2026-09-20
Comments: 30 pages
Code: https://github.com/Lapiths/LAPITHS-FRAMEWORK
License: http://creativecommons.org/licenses/by-sa/4.0/
The gist: We introduce a framework called LAPITHS (Language model Analysis through Paradigm grounded Interpretations of Theses about Human likenesS) and use it to show that several major claims advanced by
Terminology
Abstract
We introduce a framework called LAPITHS (Language model Analysis through Paradigm grounded Interpretations of Theses about Human likenesS) and use it to show that several major claims advanced by models such as CENTAUR, proposed as an artificial Unified Model of Cognition, are not theoretically or empirically justified. LAPITHS provides a principled reference point for counteracting the current behaviouristic tendency in AI research to interpret the human level performances of transformer based language models as evidence of human like underlying computation and, by extension, as signs of cognitive abilities. The novelty of LAPITHS lies in making explicit the arguments grounded in two quantitative assessments: (i) the Minimal Cognitive Grid, a theoretically motivated method for estimating the cognitive plausibility of artificial systems, and (ii) a behavioural comparison showing that results similar to those reported for CENTAUR like models can be reproduced by other systems that do not satisfy the structural constraints typically associated with cognitive plausibility, and whose outputs do not provide independent explanatory insight into human cognition.
Sources
- On the Opportunities and Risks of Foundation Models
- World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Child
- The Llama 3 Herd of Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- World Models
- LoRA: Low-Rank Adaptation of Large Language Models
- Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
- Memory in the Age of AI Agents
- Large Language Model probabilities cannot distinguish between possible and impossible language
- Large Language Diffusion Models
- Not Even Wrong: On the Limits of Prediction as Explanation in Cognitive Science
- Epistemological Fault Lines Between Human and Artificial Intelligence
- LLaMA: Open and Efficient Foundation Language Models
- Addressing Longstanding Challenges in Cognitive Science with Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection