Ethics, Rules of Engagement, and AI: Neural Narrative Mapping Using Large Transformer Language Models

TL;DR

This paper introduces Neural Narrative Maps (NNMs), a novel method using large transformer language models like GPT-3 to visualize and analyze the organization of information, intent, and belief within the model for military command verification.

Contribution

The paper presents a new approach to mapping information spaces in language models, specifically applying it to assess subordinate intent in military command scenarios using GPT-3.

Findings

High-quality narrative maps generated from GPT-3

Ability to evaluate subordinate intent and orientation

Demonstrates new methods for understanding model's internal organization

Abstract

The problem of determining if a military unit has correctly understood an order and is properly executing on it is one that has bedeviled military planners throughout history. The advent of advanced language models such as OpenAI's GPT-series offers new possibilities for addressing this problem. This paper presents a mechanism to harness the narrative output of large language models and produce diagrams or "maps" of the relationships that are latent in the weights of such models as the GPT-3. The resulting "Neural Narrative Maps" (NNMs), are intended to provide insight into the organization of information, opinion, and belief in the model, which in turn provide means to understand intent and response in the context of physical distance. This paper discusses the problem of mapping information spaces in general, and then presents a concrete implementation of this concept in the context of OpenAI's GPT-3 language model for determining if a subordinate is following a commander's intent in a high-risk situation. The subordinate's locations within the NNM allow a novel capability to evaluate the intent of the subordinate with respect to the commander. We show that is is possible not only to determine if they are nearby in narrative space, but also how they are oriented, and what "trajectory" they are on. Our results show that our method is able to produce high-quality maps, and demonstrate new ways of evaluating intent more generally.