paper-with-me

홈 › Papers

"Explanation" is Not a Technical Term: The Problem of Ambiguity in XAI

2022-06-27 · Leilani H. Gilpin, Andrew R. Paley, Mohammed A. Alam, Sarah Spurlock, Kristian J. Hammond

There is broad agreement that Artificial Intelligence (AI) systems, particularly those using Machine Learning (ML), should be able to "explain" their behavior. Unfortunately, there is little agreement as to what constitutes an "explanation." This has caused a disconnect between the explanations that systems produce in service of explainable Artificial Intelligence (XAI) and those explanations that users and other audiences actually need, which should be defined by the full spectrum of functional roles, audiences, and capabilities for explanation. In this paper, we explore the features of explanations and how to use those features in evaluating their utility. We focus on the requirements for explanations defined by their functional role, the knowledge states of users who are trying to understand them, and the availability of the information needed to generate them. Further, we discuss the risk of XAI enabling trust in systems without establishing their trustworthiness and define a critical next step for the field of XAI to establish metrics to guide and ground the utility of system-generated explanations.

📄 PDF Abstract BibTeX arXiv:2207.00007

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis

2026-06-11 · Fabrizio Marozzo, Pietro Liò arxiv

Large language models (LLMs) are increasingly used as interactive assistants for technical problem solving. However, when users provide incomplete descriptions or plausible but unverified explanations, LLMs may premature…

Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts

2022-01-25 · Sebastian Bordt, Michèle Finck, Eric Raidl, Ulrike Von Luxburg

Existing and planned legislation stipulates various obligations to provide information about machine learning algorithms and their functioning, often interpreted as obligations to "explain". Many researchers suggest usin…

A Comprehensive Perspective on Explainable AI across the Machine Learning Workflow

2025-08-15 · George Paterakis, Andrea Castellani, George Papoutsoglou, Tobias Rodemann 외 arxiv

Artificial intelligence is reshaping science and industry, yet many users still regard its models as opaque "black boxes". Conventional explainable artificial-intelligence methods clarify individual predictions but overl…

Rashomon in the Streets: Explanation Ambiguity in Scene Understanding

2025-09-03 · Helge Spieker, Jørn Eirik Betten, Arnaud Gotlieb, Nadjib Lazaar 외 arxiv

Explainable AI (XAI) is essential for validating and trusting models in safety-critical applications like autonomous driving. However, the reliability of XAI is challenged by the Rashomon effect, where multiple, equally …

Scene UnderstandingAutonomous Driving

Explaining the Ambiguity of Object Detection and 6D Pose From Visual Data

2018-12-01 · ICCV 2019 10 · Fabian Manhardt, Diego Martin Arroyo, Christian Rupprecht, Benjamin Busam 외

3D object detection and pose estimation from a single image are two inherently ambiguous problems. Oftentimes, objects appear similar from different viewpoints due to shape symmetries, occlusion and repetitive textures. …

3D Object DetectionObjectobject-detectionObject Detection+2