PhilSci Archive

Taxonomy of Risks posed by Language Models

Kasirzadeh, Atoosa (2022) Taxonomy of Risks posed by Language Models. FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency. pp. 214-229.

[img]
Preview
Text
3531146.3533088.pdf

Download (737kB) | Preview

Abstract

Responsible innovation on large-scale Language Models (LMs) re- quires foresight into and in-depth understanding of the risks these models may pose. This paper develops a comprehensive taxon- omy of ethical and social risks associated with LMs. We identify twenty-one risks, drawing on expertise and literature from com- puter science, linguistics, and the social sciences. We situate these risks in our taxonomy of six risk areas: I. Discrimination, Hate speech and Exclusion, II. Information Hazards, III. Misinformation Harms, IV. Malicious Uses, V. Human-Computer Interaction Harms, and VI. Environmental and Socioeconomic harms. For risks that have already been observed in LMs, the causal mechanism leading to harm, evidence of the risk, and approaches to risk mitigation are discussed. We further describe and analyse risks that have not yet been observed but are anticipated based on assessments of other language technologies, and situate these in the same taxonomy. We underscore that it is the responsibility of organizations to engage with the mitigations we discuss throughout the paper. We close by highlighting challenges and directions for further research on risk evaluation and mitigation with the goal of ensuring that language models are developed responsibly.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Published Article or Volume
Creators:
CreatorsEmailORCID
Kasirzadeh, Atoosaatoosa.kasirzadeh@mail.utoronto.ca
Keywords: Ethics of artificial intelligence; responsible AI; philosophy of machine learning; large language models; language technologies
Subjects: Specific Sciences > Artificial Intelligence
General Issues > Ethical Issues
General Issues > Technology
Depositing User: Dr. Atoosa Kasirzadeh
Date Deposited: 08 Dec 2022 15:30
Last Modified: 08 Dec 2022 15:30
Item ID: 21523
Journal or Publication Title: FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency
Publisher: ACM
Official URL: https://dl.acm.org/doi/abs/10.1145/3531146.3533088
Subjects: Specific Sciences > Artificial Intelligence
General Issues > Ethical Issues
General Issues > Technology
Date: 2022
Page Range: pp. 214-229
URI: https://philsci-archive-dev.library.pitt.edu/id/eprint/21523

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item