Towards Benchmarking the Utility of Explanations for Model Debugging
Post-hoc explanation methods are an important class of approaches that help understand the rationale underlying a trained model's decision. But how useful are they for an end-user towards accomplishing a given task? In this vision paper, we argue the need for a benchmark to facilitate evaluations of the utility of post-hoc explanation methods. As a first step to this end, we enumerate desirable properties that such a benchmark should possess for the task of debugging text classifiers. Additionally, we highlight that such a benchmark facilitates not only assessing the effectiveness of explanations but also their efficiency.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingSimilar Papers 제목 키워드 기반
XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models
NLP models are susceptible to learning spurious biases (i.e., bugs) that work on some datasets but do not properly reflect the underlying task. Explanation-based model debugging aims to resolve spurious biases by showing…
text-classificationText ClassificationFrom Attribution to Action: A Human-Centered Application of Activation Steering
Explainable AI (XAI) methods reveal which features influence model predictions, yet provide limited means for practitioners to act on these explanations. Activation steering of components identified via XAI offers a path…
FairX: A comprehensive benchmarking tool for model analysis using fairness, utility, and explainability
We present FairX, an open-source Python-based benchmarking tool designed for the comprehensive analysis of models under the umbrella of fairness, utility, and eXplainability (XAI). FairX enables users to train benchmarki…
BenchmarkingFairnessDet-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection
Despite the rapid uptake of black-box object detectors in marine mammal research and monitoring, explainability techniques are rarely integrated into conservation workflows. Furthermore, most classification-oriented expl…
Data AugmentationNeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations
Despite deep learning (DL) has achieved remarkable progress in various domains, the DL models are still prone to making mistakes. This issue necessitates effective debugging tools for DL practitioners to interpret the de…
counterfactualDecision MakingImage Classification