Ethics2vec: aligning automatic agents and human preferences

TL;DR

Ethics2Vec introduces a method to represent and compare AI decision-making strategies with human ethical values using vector embeddings, addressing the challenge of aligning AI systems with complex, incommensurable human values.

Contribution

The paper extends the Anything2Vec approach to ethics, proposing a vectorization method for automatic agents to assess alignment with human values.

Findings

Proposes Ethics2Vec for ethical alignment of AI agents.

Demonstrates vectorization of binary decision-making.

Extends approach to automatic control systems.

Abstract

Though intelligent agents are supposed to improve human experience (or make it more efficient), it is hard from a human perspective to grasp the ethical values which are explicitly or implicitly embedded in an agent behaviour. This is the well-known problem of alignment, which refers to the challenge of designing AI systems that align with human values, goals and preferences. This problem is particularly challenging since most human ethical considerations refer to \emph{incommensurable} (i.e. non-measurable and/or incomparable) values and criteria. Consider, for instance, a medical agent prescribing a treatment to a cancerous patient. How could it take into account (and/or weigh) incommensurable aspects like the value of a human life and the cost of the treatment? Now, the alignment between human and artificial values is possible only if we define a common space where a metric can be defined and used. This paper proposes to extend to ethics the conventional Anything2vec approach, which has been successful in plenty of similar and hard-to-quantify domains (ranging from natural language processing to recommendation systems and graph analysis). This paper proposes a way to map an automatic agent decision-making (or control law) strategy to a multivariate vector representation, which can be used to compare and assess the alignment with human values. The Ethics2Vec method is first introduced in the case of an automatic agent performing binary decision-making. Then, a vectorisation of an automatic control law (like in the case of a self-driving car) is discussed to show how the approach can be extended to automatic control settings.