Trends in Explainable AI (XAI) Literature
This work provides a resource for researchers to systematically study and discover XAI papers, addressing a practical need in the field.
The authors tackled the problem of decentralized and inconsistent terminology in Explainable AI (XAI) literature by creating a curated dataset of 5,199 papers, which they used to analyze trends such as increasing multidisciplinary collaboration and citation activity.
The XAI literature is decentralized, both in terminology and in publication venues, but recent years saw the community converge around keywords that make it possible to more reliably discover papers automatically. We use keyword search using the SemanticScholar API and manual curation to collect a well-formatted and reasonably comprehensive set of 5199 XAI papers, available at https://github.com/alonjacovi/XAI-Scholar . We use this collection to clarify and visualize trends about the size and scope of the literature, citation trends, cross-field trends, and collaboration trends. Overall, XAI is becoming increasingly multidisciplinary, with relative growth in papers belonging to increasingly diverse (non-CS) scientific fields, increasing cross-field collaborative authorship, increasing cross-field citation activity. The collection can additionally be used as a paper discovery engine, by retrieving XAI literature which is cited according to specific constraints (for example, papers that are influential outside of their field, or influential to non-XAI research).