Leveraging Argumentation for Generating Robust Sample-based Explanations

Authors: Leila Amgoud, Philippe Muller, Henri Trenquier

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The fourth contribution is an experimental analysis of the functions on various datasets. The results confirm that abductive explanations that are generated from datasets (as done by Anchors) are generally incorrect. They show also that the new functions which guarantee correctness perform well as they explain quite an important proportion of instances.
Researcher Affiliation Academia Leila Amgoud1 , Philippe Muller2 and Henri Trenquier3 1CNRS IRIT 2Toulouse University IRIT 3Toulouse University ANITI {leila.amgoud, philippe.muller}@irit.fr, henri.trenquier@univ-tlse3.fr
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No Details on the implementation are given in the supplementary material.
Open Datasets Yes We tested the four functions on various datasets, namely diabetes, titanic available on the Kaggle website, and lending adult (shortened) and recidivism (shortened) that are available on Anchors experiments [Ribeiro et al., 2018].
Dataset Splits No The paper mentions using 'training instances' and 'dataset on which R is trained' for the general context of classifiers, and discusses generating arguments from 'different percentages of the whole space', but it does not specify the train/validation/test splits for the datasets used in its own experiments.
Hardware Specification No The paper does not provide any specific hardware specifications (e.g., CPU, GPU models, or memory details) used for running its experiments.
Software Dependencies No The paper mentions that five functions were implemented, but it does not provide specific software dependencies or version numbers.
Experiment Setup No The paper does not provide specific experimental setup details such as hyperparameter values or training configurations in the main text. It only vaguely states that 'Details on the implementation are given in the supplementary material.'