Explainable AI Reloaded: Challenging the XAI Status Quo in the Era of Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929458124947456 |
|---|---|
| author | Ehsan, Upol Riedl, Mark O. |
| author_facet | Ehsan, Upol Riedl, Mark O. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_05345 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explainable AI Reloaded: Challenging the XAI Status Quo in the Era of Large Language Models Ehsan, Upol Riedl, Mark O. Human-Computer Interaction Artificial Intelligence 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. |
| title | Explainable AI Reloaded: Challenging the XAI Status Quo in the Era of Large Language Models |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2408.05345 |