Towards a Benchmark for Scientific Understanding in Humans and Machines

TL;DR

This paper proposes a new benchmark, SUB, to measure and compare scientific understanding in humans and AI, using behavioral tasks inspired by philosophy of science.

Contribution

It introduces a framework and set of tests for evaluating scientific understanding, bridging human and machine capabilities.

Findings

SUB enables comparison of scientific understanding levels

Benchmarking improves trust and quality in AI understanding

Aligning human and machine understanding advances scientific discovery

Abstract

Scientific understanding is a fundamental goal of science, allowing us to explain the world. There is currently no good way to measure the scientific understanding of agents, whether these be humans or Artificial Intelligence systems. Without a clear benchmark, it is challenging to evaluate and compare different levels of and approaches to scientific understanding. In this Roadmap, we propose a framework to create a benchmark for scientific understanding, utilizing tools from philosophy of science. We adopt a behavioral notion according to which genuine understanding should be recognized as an ability to perform certain tasks. We extend this notion by considering a set of questions that can gauge different levels of scientific understanding, covering information retrieval, the capability to arrange information to produce an explanation, and the ability to infer how things would be different under different circumstances. The Scientific Understanding Benchmark (SUB), which is formed by a set of these tests, allows for the evaluation and comparison of different approaches. Benchmarking plays a crucial role in establishing trust, ensuring quality control, and providing a basis for performance evaluation. By aligning machine and human scientific understanding we can improve their utility, ultimately advancing scientific understanding and helping to discover new insights within machines.