Explore groundbreaking research papers on Explainable AI that provide deep insights and advancements in making AI systems understandable to humans. Stay up-to-date with leading methodologies and significant findings that are shaping the future of AI explainability. Delve into top research works that ensure AI transparency, helping to bridge the gap between complex models and user comprehension.
Looking for research-backed answers?Try AI Search
A new frontier is opening for researchers in explainability and explainable AI, where a new frontier is opening for researchers to interpret the behavior and predictions of neural networks.
David Gunning, M. Stefik, Jaesik Choi + 3 more
Science Robotics
This research presents a meta-modelling architecture that automates the very labor-intensive and therefore time-heavy and therefore expensive and expensive process of manually cataloging and cataloging artificial intelligence applications.
Michael Ridley
Information Technology and Libraries
The field of explainable artificial intelligence (XAI) advances techniques, processes, and strategies that provide explanations for the predictions, recommendations, and decisions of opaque and complex machine learning systems. Increasingly academic libraries are providing library users with systems, services, and collections created and delivered by machine learning. Academic libraries should adopt XAI as a tool set to verify and validate these resources, and advocate for public policy regarding XAI that serves libraries, the academy, and the public interest.
Ranu Sewada, Ashwani Jangid, Piyush Kumar + 1 more
international journal of food and nutritional sciences
This research paper delves into the essence of XAI, unraveling its significance across diverse domains such as healthcare, finance, and criminal justice and scrutinizes the delicate balance between interpretability and performance, shedding light on instances where the pursuit of accuracy may compromise explain-ability.
G. Reddy, Y. V. P. Kumar
2023 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream)
An overview of XAI and its techniques for creating interpretable models, specifically focusing on Local Interpretable Model-Agnostic Explanations and SHapley Additive exPlanations are presented.
Utsab Khakurel, D. Rawat
journal unavailable
This paper investigates XAI for algorithmic trustworthiness and transparency using some example use cases and by using SHAP (SHapley Additive exPlanations) library and visualizing the effect of features individually and cumulatively in the prediction process.
Emer Owens, Barry Sheehan, Martin Mullins + 3 more
Risks
The study finds that XAI methods are particularly prevalent in claims management, underwriting and actuarial pricing practices, and proposes an adapted definition of XAI informed by the systematic review ofXAI literature in insurance.
Anil Kumar Malik
journal unavailable
This session will go over why the AI needs to be explainable, what does that mean, the state of the art of explainable AI as well as various approaches to build it.
Vinitra Swamy, Jibril Frej, Tanja Käser
ArXiv
It is postulate that the future of human-centric XAI is neither in explaining black-boxes nor in reverting to traditional, interpretable models, but in neural networks that are intrinsically interpretable.
Erico Tjoa, Cuntai Guan
IEEE Transactions on Neural Networks and Learning Systems
A review on interpretabilities suggested by different research works and categorize them is provided, hoping that insight into interpretability will be born with more considerations for medical practices and initiatives to push forward data-based, mathematically grounded, and technically grounded medical education are encouraged.
David Gunning, D. Aha
AI Mag.
In a series of ongoing evaluations, the developer teams are assessing how well their XAM systems’ explanations improve user understanding, user trust, and user task performance.
Christian Meske, B. Abedin, I. Junglas + 1 more
journal unavailable
The use of Artificial Intelligence in the context of decision analytics and service science has received significant attention in academia and practice alike, but much of the current efforts have focused on advancing underlying algorithms and not on decreasing the complexity of AI systems.
Zvjezdana Krstić, Mirjana Maksimović
Proceedings of the 29th International Scientific Conference Strategic Management and Decision Support Systems in Strategic Management
The key role of XAI in shaping future trends in marketing research and its implications for businesses operating in a dynamic market environment are highlighted, with the aim of driving marketing practices in a data-dominated era.
V. Chamola, Vikas Hassija, A. Sulthana + 3 more
IEEE Access
This paper presents a comprehensive review of the state-of-the-art on how to build a Trustworthy and eXplainable AI, taking into account that AI is a black box with little insight into its underlying structure.
Julie Gerlings, Arisa Shollo, Ioanna D. Constantiou
journal unavailable
A systematic review of xAI literature on the topic identifies four thematic debates central to how xAI addresses the black-box problem and synthesizes the findings into a future research agenda to further the xAI body of knowledge.
David Gunning
Proceedings of the 24th International Conference on Intelligent User Interfaces
The DARPA's Explainable Artificial Intelligence (XAI) program endeavors to create AI systems whose learned models and decisions can be understood and appropriately trusted by end users. This talk will summarize the XAI program and present highlights from these Phase 1 evaluations.
F. Hussain, R. Hussain, E. Hossain
ArXiv
The remarkable advancements in Deep Learning (DL) algorithms have fueled enthusiasm for using Artificial Intelligence (AI) technologies in almost every domain; however, the opaqueness of these algorithms put a question mark on their applications in safety-critical systems. In this regard, the `explainability' dimension is not only essential to both explain the inner workings of black-box algorithms, but it also adds accountability and transparency dimensions that are of prime importance for regulators, consumers, and service providers. eXplainable Artificial Intelligence (XAI) is the set of te...
Barnaby Crook, Maximilian Schluter, Timo Speith
2023 IEEE 31st International Requirements Engineering Conference Workshops (REW)
It is argued that the supposed trade-off between explainability and performance is best approached in a nuanced way that incorporates resource availability, domain characteristics, and considerations of risk.
R. Byrne
journal unavailable
It is argued that central to the XAI endeavor is the requirement that automated explanations provided by an AI system should make sense to human users.
Yeaeun Gong, Lanyu Shang, Dong Wang
IEEE Transactions on Computational Social Systems
The significance of this article lies in introducing the “social explanation” concept in XAI, which has been underexplored in the previous literature, and demonstrating how social explanations can be effectively employed to tackle misinformation and promote collaboration across diverse fields by drawing upon interdisciplinary techniques.
Deepak Sharma, Vikash Koundilya, Shivam Verma
International Journal of Psychosocial Rehabilitation
This research targets to delve into various methodologies geared toward making those fashions greater interpretable, understandable, and in the long run extra straightforward, to bridge the space among the inherent complexity of superior device studying models and the need for obvious decision-making methods.
J. Lötsch, D. Kringel, A. Ultsch
BioMedInformatics
This review focuses on the requirement that XAIs must be able to explain in detail the decisions made by the AI to the experts in the field.
Nipuna Thalpage
Journal of Digital Art & Humanities
A conceptual review explores the significance of XAI in promoting trust and transparency in AI systems, analyzes existing literature on XAI, identifies patterns and gaps, and presents a coherent conceptual framework.
N. C. Chung, Hongkyou Chung, Hearim Lee + 3 more
ArXiv
This paper analyze legislative and policy developments in the United States and the European Union, such as the Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence, the AI Act, the AI Liability Directive, and the General Data Protection Regulation from a right to explanation perspective from a right to explanation perspective to argue that these AI regulations and current market conditions threaten effective AI governance and safety.
Arun Das, P. Rad
ArXiv
A taxonomy and categorizing the XAI techniques based on their scope of explanations, methodology behind the algorithms, and explanation level or usage which helps build trustworthy, interpretable, and self-explanatory deep learning models is proposed.
Timo Speith
Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency
This paper will review recent approaches to constructing taxonomies of XAI methods and discuss general challenges concerning them as well as their individual advantages and limitations, and propose and discuss three possible solutions.
İbrahim Kök, Feyza Yıldırım Okay, Özgecan Muyanlı + 1 more
IEEE Internet of Things Journal
An in-depth and systematic review of recent studies that use XAI models in the scope of the IoT domain and classify the studies according to their methodology and application areas.
A. Laios, D. de Jong, E. Kalampokis
Translational Cancer Research
Utilization of model-agnostic explainable artificial intelligence frameworks in oncology: a narrative explores the role of models in medicine and the role that models play in medicine's therapeutic decisions.
Tim Hulsen
AI
This narrative review will have a look at some central concepts in XAI, describe several challenges around XAI in healthcare, and discuss whether it can really help healthcare to advance by increasing understanding and trust.
G. Chaudhary
Kutafin Law Review
The argument presented is that xAI is crucial in contexts as it empowers judges to make informed decisions based on algorithmic outcomes, and the lack of transparency, in decision-making processes can impede judge's ability to do effectively.
Thomas Rojat, Raphael Puget, David Filliat + 3 more
ArXiv
This paper presents an overview of existing explainable AI (XAI) methods applied on time series and illustrates the type of explanations they produce and provides a reflection on the impact of these explanation methods to provide confidence and trust in the AI systems.
N. Shafiabady, Nick Hadjinicolaou, Nadeesha Hettikankanamage + 3 more
PLOS ONE
This study aims to demystify the decision-making processes of the prediction model using XAI, essential for the ethical deployment of AI, fostering trust and transparency in these systems.
To increase people’s trust in adopting AI models, it is important a complete interpretability of the behaviour of AI-models is shown.
Yanou Ramon, T. Vermeire, David Martens + 2 more
SSRN Electronic Journal
This work focuses on three main attributes that describe automatically-generated explanations from existing XAI algorithms (format, complexity, and specificity), and captures differences across contexts (online targeted advertising vs. loan applications) as well as heterogeneity in users’ cognitive styles.
Mr. AnilKumar, Algin M Shabu
journal unavailable
This abstract explores the necessity of using Explainable AI (XAI) to threat intelligence advancement, clarifying its importance, approaches, difficulties, and potential applications.
Dileep Kumar Pandiya, Vilas Ramrao Joshi, Kailash Nath Tripathi
2024 3rd International Conference on Computational Modelling, Simulation and Optimization (ICCMSO)
This manuscript embarks on a comprehensive exploration of the strides made in XAI, meticulously dissecting its significance, fundamental methodologies, practical applications, hurdles, ethical dimensions, and trajectories for future advancement.
Abdullah Çaglar Öksüz, Anisa Halimi, Erman Ayday
Proc. Priv. Enhancing Technol.
AUTOLYCUS, a novel retraining (learning) based model extraction attack framework against interpretable models under black-box settings, is proposed and shown to be highly effective, requiring significantly fewer queries compared to state-of-the-art attacks, while maintaining comparable accuracy and similarity.
This work uses keyword search using the SemanticScholar API and manual curation to collect a well-formatted and reasonably comprehensive set of 5199 XAI papers, to clarify and visualize trends about the size and scope of the literature, citation trends, cross-field trends, and collaboration trends.
PhD Akif B. Tosun, PhD Filippo Pullara, MD Michael J. Becich + 3 more
Advances in Anatomic Pathology
HistoMapr-Breast is described, an initial xAI enabled software application for breast core biopsies that automatically previews breast core WSIs and recognizes the regions of interest to rapidly present the key diagnostic areas in an interactive and explainable manner.
K. Sudar, P. Nagaraj, S. Nithisaa + 3 more
2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)
From this article, one can understand the analysis of Alzheimer's by using XAI with the corresponding feature explanation, so that the result is much more trustable and reliable.
Haoyi Xiong, Xuhong Li, Xiaofei Zhang + 5 more
ArXiv
This work distill XAI methodologies into data mining operations on training and testing data across modalities, such as images, text, and tabular data, as well as on training logs, checkpoints, models and other DNN behavior descriptors.
Jeetesh Sharma, Murari Lal Mittal, G. Soni + 1 more
Recent Patents on Engineering
Based on the findings, XAI techniques can bring new insights and opportunities for addressing critical maintenance issues, resulting in more informed decisions, and the results analysis suggests a viable path for future studies.
Alena I. Kalyakulina, I. Yusipov
ArXiv
A systematic review of the works organized by body systems is given, and the application of XAI approaches to age prediction tasks are discussed, in particular, in the age prediction domain.
Krishna P. Kalyanathaya, K. K.
International Journal of Applied Engineering and Management Letters
A common approach to build explainable models that may fulfill current challenges of XAI is conceptualized and brought some open research agenda in these findings and future directions.
C. Zhang, Soohyun Cho, M. Vasarhelyi
SSRN Electronic Journal
The state-of-the-art XAI techniques are introduced to accounting researchers and practitioners using terms familiar to them and a framework on how different X AI techniques can be used to meet requirements of existing auditing standards is provided.
José Luis Corcuera Bárcena, Mattia Daole, P. Ducange + 4 more
journal unavailable
The concept of Federated Learning of eXplainable AI (XAI) models, in short FED-XAI, purposely designed to address these two requirements simultaneously of preserving the data privacy and ensuring a certain level of explainability of the system.
Timo Speith, Markus Langer
2023 IEEE 31st International Requirements Engineering Conference Workshops (REW)
This novel perspective is intended to augment the perspective of other authors by focusing less on the EMs themselves but on what explainability approaches intend to achieve (i.e., provide good explanatory information, facilitate understanding, satisfy societal desiderata).
Aryan Sethi, Sahiti Dharmavaram, S. K. Somasundaram
2024 3rd International Conference on Artificial Intelligence For Internet of Things (AIIoT)
A predictive model for heart disease with 96.07% accuracy is developed, integrating factors like peak exercise ST segment slope, maximum heart rate, and exercise-induced angina, and enables interpretable predictions, facilitating early detection and informed management.
Janet Hsiao, H. Ngai, Luyu Qiu + 2 more
ArXiv
The current report aims to propose suitable metrics for evaluating XAI systems from the perspective of the cognitive states and processes of stakeholders, and elaborate on 7 dimensions, i.e., goodness, satisfaction, user understanding, curiosity&engagement, trust&reliance, controllability&interactivity, and learning curve&productivity.
Evandro S. Ortigossa, Thales Gonçalves, L. G. Nonato
IEEE Access
The theoretical foundations of Explainable Artificial Intelligence (XAI) are provided, clarifying diffuse definitions and identifying research objectives, challenges, and future research lines related to turning opaque machine learning outputs into more transparent decisions.