Explainable AI Reloaded: Challenging the XAI Status Quo in the Era of Large Language Models
arXiv:2408.05345 · doi:10.1145/3686169.3686185
Abstract
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.
Accepted to ACM HTTF 2024
References in corpus (7)
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Questioning the AI: Informing Design Practices for Explainable AI User Experiences
- Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making
- Expanding Explainability: Towards Social Transparency in AI systems
- The Pragmatic Turn in Explainable Artificial Intelligence (XAI)
- Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI
- Appropriate Fairness Perceptions? On the Effectiveness of Explanations in Enabling People to Assess the Fairness of Automated Decision Systems