Bias, machine learning, and conceptual engineering.
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...
| Publicado en: | Philosophical Studies Vol. 182; no. 7; pp. 1889 - 1918 |
|---|---|
| Autores principales: | , , |
| Formato: | Artículo |
| Publicado: |
Springer Nature
Jul2025
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=186909906&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 186909906 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00318116 4L8 jtl: Philosophical Studies issn: 00318116 maglogo: N pubinfo: dt: Jul2025 vid: 182 iid: 7 pid: 237 pub: Springer Nature artinfo: ui: 186909906 10.1007/s11098-024-02273-w ppf: 1889 ppct: 29 formats: fmt: – @attributes: type: T – @attributes: type: P size: 1.1MB tig: atl: Bias, machine learning, and conceptual engineering. aug: au: Rudolph, Rachel Etta Shech, Elay Tamir, Michael affil: https://ror.org/0168r3w48 Department of Philosophy, University of California, San Diego, 9500 Gilman Dr., 92093, La Jolla, CA, USA https://ror.org/02v80fc35 Department of Philosophy, Auburn University, 6080 Haley Center, 36849, Auburn, AL, USA https://ror.org/01an7q238 School of Information, University of California, Berkeley, 102 South Hall # 4600, 94720-4600, Berkeley, CA, USA su: Machine learning Artificial intelligence Language models Digital technology Engineering sug: subj: Machine learning Artificial intelligence Language models Digital technology Engineering keyword: AI alignment AI ethics Bias Conceptual engineering Large language models ab: 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. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Philosophical Studies is a copyright of Springer, 2025. All Rights Reserved. item: Philosophical Studies holder: Springer Nature dt: @attributes: year: 2025 holdings: @attributes: islocal: N |
|---|