paper-with-me

홈 › Papers

Towards Benchmarking the Utility of Explanations for Model Debugging

2021-05-10 · NAACL (TrustNLP) 2021 6 · Maximilian Idahl, Lijun Lyu, Ujwal Gadiraju, Avishek Anand

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.

📄 PDF Abstract BibTeX arXiv:2105.04505

Code (0)

등록된 구현이 없습니다.

Tasks

Benchmarking

Similar Papers 제목 키워드 기반

XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models

2022-10-30 · Dong-Ho Lee, Akshen Kadakia, Brihi Joshi, Aaron Chan 외

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 Classification

From Attribution to Action: A Human-Centered Application of Activation Steering

2026-04-13 · Tobias Labarta, Maximilian Dreyer, Katharina Weitz, Wojciech Samek 외 arxiv

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

2024-06-20 · Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng, Fredrik Heintz

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…

BenchmarkingFairness

Det-LIME: Detector-Aware, Multi-Instance Local Interpretable Model-Agnostic Explanations for Automated Marine Mammal Detection

2026-09-15 · Jiayi Zhou, David W. Johnston, Brinnae Bent arxiv

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 Augmentation

NeuroInspect: Interpretable Neuron-based Debugging Framework through Class-conditional Visualizations

2023-10-11 · Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee

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