Explainable AI Reloaded: Challenging the XAI Status Quo in the Era of Large Language Models
This work addresses the problem of making AI explanations accessible to non-expert users in the LLM era, proposing a shift in XAI expectations.
The paper challenges the traditional goal of 'opening the black-box' in Explainable AI (XAI) for Large Language Models (LLMs), arguing that a human-centered perspective is needed instead, and synthesizes XAI research along three dimensions to inform the domain.
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.