Conceptual Engineering Using Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Allen, Bradley P.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910680929533952
author Allen, Bradley P.
author_facet Allen, Bradley P.
contents We describe a method, based on Jennifer Nado's proposal for classification procedures as targets of conceptual engineering, that implements such procedures by prompting a large language model. We apply this method, using data from the Wikidata knowledge graph, to evaluate stipulative definitions related to two paradigmatic conceptual engineering projects: the International Astronomical Union's redefinition of PLANET and Haslanger's ameliorative analysis of WOMAN. Our results show that classification procedures built using our approach can exhibit good classification performance and, through the generation of rationales for their classifications, can contribute to the identification of issues in either the definitions or the data against which they are being evaluated. We consider objections to this method, and discuss implications of this work for three aspects of theory and practice of conceptual engineering: the definition of its targets, empirical methods for their investigation, and their practical roles. The data and code used for our experiments, together with the experimental results, are available in a Github repository.
format Preprint
id arxiv_https___arxiv_org_abs_2312_03749
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Conceptual Engineering Using Large Language Models
Allen, Bradley P.
Computation and Language
Artificial Intelligence
Computers and Society
I.2.7; I.2.4
We describe a method, based on Jennifer Nado's proposal for classification procedures as targets of conceptual engineering, that implements such procedures by prompting a large language model. We apply this method, using data from the Wikidata knowledge graph, to evaluate stipulative definitions related to two paradigmatic conceptual engineering projects: the International Astronomical Union's redefinition of PLANET and Haslanger's ameliorative analysis of WOMAN. Our results show that classification procedures built using our approach can exhibit good classification performance and, through the generation of rationales for their classifications, can contribute to the identification of issues in either the definitions or the data against which they are being evaluated. We consider objections to this method, and discuss implications of this work for three aspects of theory and practice of conceptual engineering: the definition of its targets, empirical methods for their investigation, and their practical roles. The data and code used for our experiments, together with the experimental results, are available in a Github repository.
title Conceptual Engineering Using Large Language Models
topic Computation and Language
Artificial Intelligence
Computers and Society
I.2.7; I.2.4
url https://arxiv.org/abs/2312.03749