CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks (Technical Report)
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Graph Style Transfer for Counterfactual Explainability
Performative Validity of Recourse Explanations
Generalizability vs. Counterfactual Explainability Trade-Off
Real-time Program Evaluation using Anytime-valid Rank Tests
Learning Time Series Counterfactuals via Latent Space Representations
Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs
토론
이 논문과 연결된 포럼 글이 아직 없습니다.