Skip to content
Open access

Six misconceptions about large language models: A minimal model and diagnostic taxonomy

Jul 2026 · PNAS Nexus · Vol 5 · 0 citations · 75 references
Medicine Computer Science

Abstract

Abstract Large language models (LLMs) are now embedded in scientific, educational, and governance workflows, with debates centering on their capabilities, mechanisms, and impacts. Yet these debates remain structured by persistent folk theories—intuitive, informal explanatory models that guide attitudes and actions. Deflationary slogans (“just autocomplete,” “stochastic parrots,” and “average of the internet”) and anthropomorphic framings (“emergent agents” and “proto-minds”) each capture genuine features of current systems but mistake those features for the whole. This Perspective proposes a minimal working model of LLM-based systems centered on four distinctions: between pretraining and deployed systems; between the learned distribution and particular samples; among parametric, contextual, and external memory; and between task competence and agency. The model is used to diagnose six misconceptions about LLMs: next-token prediction, regression to the mean, training-data regurgitation, model memory, alignment, and understanding. For each, the analysis identifies what the misconception gets right, which distinctions it conflates, and what follows for capability evaluation, system design, and governance. Applied to publisher AI policies as governance case studies, the framework shows both how policy language can conflate these distinctions and how such errors can be corrected. The model thereby avoids the parrot–mind binary by treating LLMs as simulators of discourse and task performance, offering a diagnostic toolkit for locating and correcting the errors these folk theories perpetuate.

Read PDF

Similar papers

Book Open access Aug 2026

Interpretability in the Era of Large Language Models: Mechanistic Methodology, Empirical Practices, and Applications

This tutorial provides a comprehensive, end-to-end view of LLM interpretability, transitioning from microscopic neural analysis to macroscopic application and deployment, and explores how these interpretability paradigms scale and inspire the design of frontier architectures, agentic systems, and thinking models.

Wei Zhang, Zhengfu He, Lucia Zhang et al. · 0 citations
Open access Jul 2026

The Socratic Trap: Benchmarking the Capacity of Large Language Models to Generate Strategic Misconceptions in Computer Science Education

SocraticTrap-CS is introduced, a publicly available benchmark that probes the capacity of open-weight LLMs to generate strategic misconceptions on demand and reframes the evaluation of educational LLMs around pedagogical trustworthiness rather than factual correctness alone.

Marijela Miličević, Mia Rovis, Ratomir Karlović et al. · 0 citations
Conference Open access 2026

The Inner Monologue of Language Models: When Reasoning Traces Reveal More Than They Hide

It is indicated that RL-trained models not only demonstrate greater awareness of their learned behaviors and stronger generalizability to novel, structurally similar tasks than SFT models but also often exhibit weak alignment between their reasoning traces and final outputs, an effect most pronounced in GRPO-trained models.

Pratham Singla, Shivank Garg, Ayush Singh et al. · 0 citations
Preprint Jul 2026

From Isolated Tasks to Structured Capabilities: A Multilayer Taxonomy for Large Language Models

A multi-layer taxonomy of 14 capability domains and 91 subskills across Primitive, Constructed, and Integrative layers is introduced and supports research organization, coverage audits, evaluation interpretation, and testable hypotheses for diagnosis, training, and transfer.

Shixin Fang, Jiachen Wo, Wenjuan Qin et al. · 0 citations
Open access Jun 2026

Dynamics of Sincerity Echo: A New Paradigm in Large Language Model Alignment Based on Cognitive Proportionality

A conceptual protocol framework called Sincerity Echo is developed as a new paradigm in LLM alignment based on Cognitive Proportionality, which can differentiate propositional expansions, low risk lightweight queries, and adversarial contradictions through a tiered validation mechanism.

Blasius Dala Nai, Jeffrey Bram Pattipeilohy, Arief Wibowo · 0 citations
Open access Aug 2026

Towards Trustworthy Large Language Models

An integrated conceptual frame-work that couples attention- and perturbation-based explainability with lightweight hallucination-detection signals and token-efficient inference strategies is presented, and a set of cross-cutting consistency metrics are instrumented with a set of cross-cutting consistency metrics.

Sakshi Parate, Shreyans Sanyal · 0 citations