TY - CHAP

T1 - Knowledge-Enhanced Language Models Are Not Bias-Proof

T2 - 2024 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2024

AU - Kraft, Angelie

AU - Soulier, Eloïse

N1 - Publisher Copyright: © 2024 Owner/Author.

PY - 2024/6/3

Y1 - 2024/6/3

N2 - The factual inaccuracies ("hallucinations") of large language models have recently inspired more research on knowledge-enhanced language modeling approaches. These are often assumed to enhance the overall trustworthiness and objectivity of language models. Meanwhile, the issue of bias is usually only mentioned as a limitation of statistical representations. This dissociation of knowledge-enhancement and bias is in line with previous research on AI engineers' assumptions about knowledge, which indicate that knowledge is commonly understood as objective and value-neutral by this community. We argue that claims and practices by actors of the field still reflect this underlying conception of knowledge. We contrast this assumption with literature from social and, in particular, feminist epistemology, which argues that the idea of a universal disembodied knower is blind to the reality of knowledge practices and seriously challenges claims of "objective"or "neutral"knowledge. Knowledge enhancement techniques commonly use Wikidata and Wikipedia as their sources for knowledge, due to their large scales, public accessibility, and assumed trustworthiness. In this work, they serve as a case study for the influence of the social setting and the identity of knowers on epistemic processes. Indeed, the communities behind Wikidata and Wikipedia are known to be male-dominated and many instances of hostile behavior have been reported in the past decade. In effect, the contents of these knowledge bases are highly biased. It is therefore doubtful that these knowledge bases would contribute to bias reduction. In fact, our empirical evaluations of RoBERTa, KEPLER, and CoLAKE, demonstrate that knowledge enhancement may not live up to the hopes of increased objectivity. In our study, the average probability for stereotypical associations was preserved on two out of three metrics and performance-related gender gaps on knowledge-driven task were also preserved. We build on these results and critical literature to argue that the label of "knowledge"and the commonly held beliefs about it can obscure the harm that is still done to marginalized groups. Knowledge enhancement is at risk of perpetuating epistemic injustice, and AI engineers' understanding of knowledge as objective per se conceals this injustice. Finally, to get closer to trustworthy language models, we need to rethink knowledge in AI and aim for an agenda of diversification and scrutiny from outgroup members.

AB - The factual inaccuracies ("hallucinations") of large language models have recently inspired more research on knowledge-enhanced language modeling approaches. These are often assumed to enhance the overall trustworthiness and objectivity of language models. Meanwhile, the issue of bias is usually only mentioned as a limitation of statistical representations. This dissociation of knowledge-enhancement and bias is in line with previous research on AI engineers' assumptions about knowledge, which indicate that knowledge is commonly understood as objective and value-neutral by this community. We argue that claims and practices by actors of the field still reflect this underlying conception of knowledge. We contrast this assumption with literature from social and, in particular, feminist epistemology, which argues that the idea of a universal disembodied knower is blind to the reality of knowledge practices and seriously challenges claims of "objective"or "neutral"knowledge. Knowledge enhancement techniques commonly use Wikidata and Wikipedia as their sources for knowledge, due to their large scales, public accessibility, and assumed trustworthiness. In this work, they serve as a case study for the influence of the social setting and the identity of knowers on epistemic processes. Indeed, the communities behind Wikidata and Wikipedia are known to be male-dominated and many instances of hostile behavior have been reported in the past decade. In effect, the contents of these knowledge bases are highly biased. It is therefore doubtful that these knowledge bases would contribute to bias reduction. In fact, our empirical evaluations of RoBERTa, KEPLER, and CoLAKE, demonstrate that knowledge enhancement may not live up to the hopes of increased objectivity. In our study, the average probability for stereotypical associations was preserved on two out of three metrics and performance-related gender gaps on knowledge-driven task were also preserved. We build on these results and critical literature to argue that the label of "knowledge"and the commonly held beliefs about it can obscure the harm that is still done to marginalized groups. Knowledge enhancement is at risk of perpetuating epistemic injustice, and AI engineers' understanding of knowledge as objective per se conceals this injustice. Finally, to get closer to trustworthy language models, we need to rethink knowledge in AI and aim for an agenda of diversification and scrutiny from outgroup members.

KW - bias

KW - epistemology

KW - fairness

KW - feminism

KW - knowledge enhancement

KW - knowledge graphs

KW - language models

KW - natural language processing

KW - representation

KW - Informatics

UR - http://www.scopus.com/inward/record.url?scp=85196640886&partnerID=8YFLogxK

U2 - 10.1145/3630106.3658981

DO - 10.1145/3630106.3658981

M3 - Article in conference proceedings

AN - SCOPUS:85196640886

T3 - 2024 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2024

SP - 1433

EP - 1445

BT - 2024 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2024

PB - Association for Computing Machinery, Inc

Y2 - 3 June 2024 through 6 June 2024

ER -