Fewer Than 1% of Explainable AI Papers Validate Explainability with Humans
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916658295078912 |
|---|---|
| author | Suh, Ashley Hurley, Isabelle Smith, Nora Siu, Ho Chit |
| author_facet | Suh, Ashley Hurley, Isabelle Smith, Nora Siu, Ho Chit |
| contents | This late-breaking work presents a large-scale analysis of explainable AI (XAI) literature to evaluate claims of human explainability. We collaborated with a professional librarian to identify 18,254 papers containing keywords related to explainability and interpretability. Of these, we find that only 253 papers included terms suggesting human involvement in evaluating an XAI technique, and just 128 of those conducted some form of a human study. In other words, fewer than 1% of XAI papers (0.7%) provide empirical evidence of human explainability when compared to the broader body of XAI literature. Our findings underscore a critical gap between claims of human explainability and evidence-based validation, raising concerns about the rigor of XAI research. We call for increased emphasis on human evaluations in XAI studies and provide our literature search methodology to enable both reproducibility and further investigation into this widespread issue. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16507 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fewer Than 1% of Explainable AI Papers Validate Explainability with Humans Suh, Ashley Hurley, Isabelle Smith, Nora Siu, Ho Chit Human-Computer Interaction Artificial Intelligence This late-breaking work presents a large-scale analysis of explainable AI (XAI) literature to evaluate claims of human explainability. We collaborated with a professional librarian to identify 18,254 papers containing keywords related to explainability and interpretability. Of these, we find that only 253 papers included terms suggesting human involvement in evaluating an XAI technique, and just 128 of those conducted some form of a human study. In other words, fewer than 1% of XAI papers (0.7%) provide empirical evidence of human explainability when compared to the broader body of XAI literature. Our findings underscore a critical gap between claims of human explainability and evidence-based validation, raising concerns about the rigor of XAI research. We call for increased emphasis on human evaluations in XAI studies and provide our literature search methodology to enable both reproducibility and further investigation into this widespread issue. |
| title | Fewer Than 1% of Explainable AI Papers Validate Explainability with Humans |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2503.16507 |