Shared Model of Sense-making for Human-Machine Collaboration
It addresses the challenge of effective collaboration between humans and AI agents in complex analysis tasks, though it appears incremental as it builds on existing scientific methods.
The paper tackles the problem of human-machine collaboration in sense-making by introducing a model grounded in evidence science and the scientific method, enabling an analyst to instruct an agent to understand complex situations like weapons production, with the agent becoming more competent across related domains.
We present a model of sense-making that greatly facilitates the collaboration between an intelligent analyst and a knowledge-based agent. It is a general model grounded in the science of evidence and the scientific method of hypothesis generation and testing, where sense-making hypotheses that explain an observation are generated, relevant evidence is then discovered, and the hypotheses are tested based on the discovered evidence. We illustrate how the model enables an analyst to directly instruct the agent to understand situations involving the possible production of weapons (e.g., chemical warfare agents) and how the agent becomes increasingly more competent in understanding other situations from that domain (e.g., possible production of centrifuge-enriched uranium or of stealth fighter aircraft).