Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.14304 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910441426386944 |
|---|---|
| author | Yin, Xiang Nico, Potyka Toni, Francesca |
| author_facet | Yin, Xiang Nico, Potyka Toni, Francesca |
| contents | Quantitatively explaining the strength of arguments under gradual semantics has recently received increasing attention. Specifically, several works in the literature provide quantitative explanations by computing the attribution scores of arguments. These works disregard the importance of attacks and supports, even though they play an essential role when explaining arguments' strength. In this paper, we propose a novel theory of Relation Attribution Explanations (RAEs), adapting Shapley values from game theory to offer fine-grained insights into the role of attacks and supports in quantitative bipolar argumentation towards obtaining the arguments' strength. We show that RAEs satisfy several desirable properties. We also propose a probabilistic algorithm to approximate RAEs efficiently. Finally, we show the application value of RAEs in fraud detection and large language models case studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_14304 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explaining Arguments' Strength: Unveiling the Role of Attacks and Supports (Technical Report) Yin, Xiang Nico, Potyka Toni, Francesca Artificial Intelligence Quantitatively explaining the strength of arguments under gradual semantics has recently received increasing attention. Specifically, several works in the literature provide quantitative explanations by computing the attribution scores of arguments. These works disregard the importance of attacks and supports, even though they play an essential role when explaining arguments' strength. In this paper, we propose a novel theory of Relation Attribution Explanations (RAEs), adapting Shapley values from game theory to offer fine-grained insights into the role of attacks and supports in quantitative bipolar argumentation towards obtaining the arguments' strength. We show that RAEs satisfy several desirable properties. We also propose a probabilistic algorithm to approximate RAEs efficiently. Finally, we show the application value of RAEs in fraud detection and large language models case studies. |
| title | Explaining Arguments' Strength: Unveiling the Role of Attacks and Supports (Technical Report) |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2404.14304 |