Conceptual Engineering Using Large Language Models

Conceptual engineering (CE) is a philosophical methodology concerned with the assessment and improvement of concepts [1]. Koch, Löhr and Pinder have surveyed recent work on the theory of CE, discussing different theories defining the targets of CE, i.e., "what conceptual engineers are (or should be) trying to engineer" [2]. In one such theory, Nado proposes as targets classification procedures, defined as abstract'recipes' which sort entities "into an'in'-group and an'out'-group" [3]. Our work builds on Nado's idea by defining a method for implementing classification procedures consistent with this definition. A large language model (LLM) is a probabilistic model trained on a natural language corpus that, given a sequence of tokens from a vocabulary occurring in the corpus, generates a continuation of the input sequence.