Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.08497 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917832253505536 |
|---|---|
| author | Yin, Xiang Potyka, Nico Toni, Francesca |
| author_facet | Yin, Xiang Potyka, Nico Toni, Francesca |
| contents | There is a growing interest in understanding arguments' strength in Quantitative Bipolar Argumentation Frameworks (QBAFs). Most existing studies focus on attribution-based methods that explain an argument's strength by assigning importance scores to other arguments but fail to explain how to change the current strength to a desired one. To solve this issue, we introduce counterfactual explanations for QBAFs. We discuss problem variants and propose an iterative algorithm named Counterfactual Explanations for Quantitative bipolar Argumentation frameworks (CE-QArg). CE-QArg can identify valid and cost-effective counterfactual explanations based on two core modules, polarity and priority, which help determine the updating direction and magnitude for each argument, respectively. We discuss some formal properties of our counterfactual explanations and empirically evaluate CE-QArg on randomly generated QBAFs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08497 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks (Technical Report) Yin, Xiang Potyka, Nico Toni, Francesca Artificial Intelligence There is a growing interest in understanding arguments' strength in Quantitative Bipolar Argumentation Frameworks (QBAFs). Most existing studies focus on attribution-based methods that explain an argument's strength by assigning importance scores to other arguments but fail to explain how to change the current strength to a desired one. To solve this issue, we introduce counterfactual explanations for QBAFs. We discuss problem variants and propose an iterative algorithm named Counterfactual Explanations for Quantitative bipolar Argumentation frameworks (CE-QArg). CE-QArg can identify valid and cost-effective counterfactual explanations based on two core modules, polarity and priority, which help determine the updating direction and magnitude for each argument, respectively. We discuss some formal properties of our counterfactual explanations and empirically evaluate CE-QArg on randomly generated QBAFs. |
| title | CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks (Technical Report) |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2407.08497 |