Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.08379 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909105125326848 |
|---|---|
| author | Wan, Charles Belo, Rodrigo Zejnilović, Leid Lavado, Susana |
| author_facet | Wan, Charles Belo, Rodrigo Zejnilović, Leid Lavado, Susana |
| contents | An algorithm effects a causal representation of relations between features and labels in the human's perception. Such a representation might conflict with the human's prior belief. Explanations can direct the human's attention to the conflicting feature and away from other relevant features. This leads to causal overattribution and may adversely affect the human's information processing. In a field experiment we implemented an XGBoost-trained model as a decision-making aid for counselors at a public employment service to predict candidates' risk of long-term unemployment. The treatment group of counselors was also provided with SHAP. The results show that the quality of the human's decision-making is worse when a feature on which the human holds a conflicting prior belief is displayed as part of the explanation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_08379 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Duet of Representations and How Explanations Exacerbate It Wan, Charles Belo, Rodrigo Zejnilović, Leid Lavado, Susana Human-Computer Interaction Machine Learning An algorithm effects a causal representation of relations between features and labels in the human's perception. Such a representation might conflict with the human's prior belief. Explanations can direct the human's attention to the conflicting feature and away from other relevant features. This leads to causal overattribution and may adversely affect the human's information processing. In a field experiment we implemented an XGBoost-trained model as a decision-making aid for counselors at a public employment service to predict candidates' risk of long-term unemployment. The treatment group of counselors was also provided with SHAP. The results show that the quality of the human's decision-making is worse when a feature on which the human holds a conflicting prior belief is displayed as part of the explanation. |
| title | The Duet of Representations and How Explanations Exacerbate It |
| topic | Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2402.08379 |