Generating Context-Aware Contrastive Explanations in Rule-based Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913237941878784 |
|---|---|
| author | Herbold, Lars Sadeghi, Mersedeh Vogelsang, Andreas |
| author_facet | Herbold, Lars Sadeghi, Mersedeh Vogelsang, Andreas |
| contents | Human explanations are often contrastive, meaning that they do not answer the indeterminate "Why?" question, but instead "Why P, rather than Q?". Automatically generating contrastive explanations is challenging because the contrastive event (Q) represents the expectation of a user in contrast to what happened. We present an approach that predicts a potential contrastive event in situations where a user asks for an explanation in the context of rule-based systems. Our approach analyzes a situation that needs to be explained and then selects the most likely rule a user may have expected instead of what the user has observed. This contrastive event is then used to create a contrastive explanation that is presented to the user. We have implemented the approach as a plugin for a home automation system and demonstrate its feasibility in four test scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13000 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generating Context-Aware Contrastive Explanations in Rule-based Systems Herbold, Lars Sadeghi, Mersedeh Vogelsang, Andreas Software Engineering Human explanations are often contrastive, meaning that they do not answer the indeterminate "Why?" question, but instead "Why P, rather than Q?". Automatically generating contrastive explanations is challenging because the contrastive event (Q) represents the expectation of a user in contrast to what happened. We present an approach that predicts a potential contrastive event in situations where a user asks for an explanation in the context of rule-based systems. Our approach analyzes a situation that needs to be explained and then selects the most likely rule a user may have expected instead of what the user has observed. This contrastive event is then used to create a contrastive explanation that is presented to the user. We have implemented the approach as a plugin for a home automation system and demonstrate its feasibility in four test scenarios. |
| title | Generating Context-Aware Contrastive Explanations in Rule-based Systems |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2402.13000 |