Explainable AI Reloaded: Challenging the XAI Status Quo in the Era of Large Language Models

Autor:	Ehsan, Upol, Riedl, Mark O.
Rok vydání:	2024
Předmět:	Computer Science - Human-Computer Interaction Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
DOI:	10.1145/3686169.3686185
Popis:	When the initial vision of Explainable (XAI) was articulated, the most popular framing was to open the (proverbial) "black-box" of AI so that we could understand the inner workings. With the advent of Large Language Models (LLMs), the very ability to open the black-box is increasingly limited especially when it comes to non-AI expert end-users. In this paper, we challenge the assumption of "opening" the black-box in the LLM era and argue for a shift in our XAI expectations. Highlighting the epistemic blind spots of an algorithm-centered XAI view, we argue that a human-centered perspective can be a path forward. We operationalize the argument by synthesizing XAI research along three dimensions: explainability outside the black-box, explainability around the edges of the black box, and explainability that leverages infrastructural seams. We conclude with takeaways that reflexively inform XAI as a domain. Comment: Accepted to ACM HTTF 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2408.05345 Zobrazit plný text záznamu View this record from Arxiv