Rudolph, Rachel and Shech, Elay and Tamir, Michael (2024) Bias, Machine Learning, and Conceptual Engineering. [Preprint]

Text BiasML_CE_2024_preprint.pdf Download (589kB)

Abstract

Large language models (LLMs) such as OpenAI’s ChatGPT reflect, and can potentially perpetuate, social biases in language use. Conceptual engineering aims to revise our concepts to eliminate such bias. We show how machine learning and conceptual engineering can be fruitfully brought together to offer new insights to both conceptual engineers and LLM designers. Specifically, we suggest that LLMs can be used to detect and expose bias in the prototypes associated with concepts, and that LLM de-biasing can serve conceptual engineering projects that aim to revise such conceptual prototypes. At present, these de-biasing techniques primarily involve approaches requiring bespoke interventions based on choices of the algorithm’s designers. Thus, conceptual engineering through de-biasing will include making choices about what kind of normative training an LLM should receive, especially with respect to different notions of bias. This offers a new perspective on what conceptual engineering involves and how it can be implemented. And our conceptual engineering approach also offers insight, to those engaged in LLM de-biasing, into the normative distinctions that are needed for that work.

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Preprint
Creators:	Creators Email ORCID Rudolph, Rachel rrudolph@ucsd.edu Shech, Elay eshech@gmail.com Tamir, Michael mntamir@gmail.com
Keywords:	Bias, Machine Learning, AI, Conceptual Engineering
Subjects:	Specific Sciences > Artificial Intelligence > AI and Ethics General Issues > Ethical Issues Specific Sciences > Artificial Intelligence > Machine Learning General Issues > Values In Science
Depositing User:	Dr. Elay Shech
Date Deposited:	13 Dec 2024 15:42
Last Modified:	13 Dec 2024 15:42
Item ID:	24397
Subjects:	Specific Sciences > Artificial Intelligence > AI and Ethics General Issues > Ethical Issues Specific Sciences > Artificial Intelligence > Machine Learning General Issues > Values In Science
Date:	13 December 2024
URI:	https://philsci-archive.pitt.edu/id/eprint/24397

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item