The Novelty Horizon H N: Why Large Language Models Fail to Generate Scientific Data beyond Their Training Distribution

arXiv:2611.05175 · eess.SY, cs.SY · Submitted 2026-11-03 · Read on arXiv

eess.SY, cs.SY

Submitted: 2026-11-03

Updated: 2026-11-03

Comments: 10 Figures, 61 pages

License: http://creativecommons.org/licenses/by/4.0/

The gist: Large Language Models (LLMs) lack physical grounding and extrapolation.

Terminology

Abstract

Large Language Models (LLMs) lack physical grounding and extrapolation. This paper formalises the Novelty Horizon as tasks needing extrapolation beyond training support, causal reasoning absent from learned correlations, or post-frontier information. A forensic analysis tests LLMs on unguided, guided, and ground-truth data from an underrepresented diode-clamped short-circuit experiment using temporal, spectral, and statistical validation against a first-principles Modified Ohm's Law. Both script-based approaches fail catastrophically with physical and spectral inconsistencies, extreme statistical pathologies, zero Generative Fidelity Score, and linear-regime outputs. Direct prompting corroborates distinct failure modes. This paper introduces the Past Information Boundary and physics-based authentication. LLM data generation cannot extrapolate past the Novelty Horizon essential for novel discovery. Hybrid neuro-symbolic systems must preserve human causal reasoning and experimental design.

Sources

Related papers