Paper presented at FAccT 2024
18 June 2024, by Angelie Kraft
On June 4, 2024, Angelie Kraft presented her paper entitled "Knowledge-Enhanced Language Models Are Not Bias-Proof: Situated Knowledge and Epistemic Injustice in AI" together with her co-author Eloïse Soulier (EIT) at the 2024 Conference on Fairness, Accountability, and Transparency in Rio de Janeiro, Brazil. This work is an interdisciplinary critique of knowledge-enhancement. It questions the unreflected use of large-scale knowledge bases like Wikipedia for the improvement of language models from a computer science and philosophy perspective.
Abstract:
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 knowledgeenhancement 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.