Strategic Doctrine Language Models (sdLM): A Learning-System Framework for Doctrinal Consistency and Geopolitical Forecasting

TL;DR

sdLM is a novel learning-system framework that enhances strategic reasoning, doctrinal consistency, and long-term geopolitical forecasting by combining multi-document attention, temporal encoding, and consistency constraints, outperforming general LLMs.

Contribution

The paper introduces sdLM, a new framework integrating doctrinal constraints with multi-document reasoning for improved strategic forecasting and doctrinal consistency in language models.

Findings

sdLM outperforms strong LLM baselines in strategic quality and calibration.

sdLM remains competitive with human experts on long-horizon judgments.

Ablation studies reveal key components driving performance improvements.

Abstract

We introduce Strategic Doctrine Language Models (sdLM), a learning-system framework for multi-document strategic reasoning with doctrinal consistency constraints and calibrated uncertainty. The approach combines multi-document attention, temporal encoding, and a doctrine-consistency layer to improve long-horizon forecasting and plan plausibility while reducing severe doctrinal violations. We evaluate sdLM using (i) expert-panel scoring of strategic scenarios (N=47), (ii) doctrine consistency on 336 doctrine publications (12,847 statements), and (iii) geopolitical forecasting on 127 historical counterfactuals (1945-2020) across 12-60 month horizons. Across these benchmarks, sdLM achieves higher strategic quality and better calibration than strong general-purpose LLM baselines, and remains competitive with human experts on long-horizon judgments. We further report ablations, scaling trends, and deployment-oriented performance/latency characteristics to clarify which components drive improvements and how they translate to operational settings.