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.
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.· Proceedings of the 32nd ACM...· 0 citations
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.· Information· 0 citations
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.· Annual Meeting of the Associ...· 0 citations
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
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· Greenation International Jou...· 0 citations
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· Advanced International Journ...· 0 citations