From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable ai

M Nauta, J Trienes, S Pathak, E Nguyen… - ACM Computing …, 2023‏ - dl.acm.org
The rising popularity of explainable artificial intelligence (XAI) to understand high-performing
black boxes raised the question of how to evaluate explanations of machine learning (ML) …

Interpretable and explainable machine learning: A methods‐centric overview with concrete examples

R Marcinkevičs, JE Vogt - Wiley Interdisciplinary Reviews: Data …, 2023‏ - Wiley Online Library
Interpretability and explainability are crucial for machine learning (ML) and statistical
applications in medicine, economics, law, and natural sciences and form an essential …

[HTML][HTML] Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence

S Ali, T Abuhmed, S El-Sappagh, K Muhammad… - Information fusion, 2023‏ - Elsevier
Artificial intelligence (AI) is currently being utilized in a wide range of sophisticated
applications, but the outcomes of many AI models are challenging to comprehend and trust …

Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes

CY Hsieh, CL Li, CK Yeh, H Nakhost, Y Fujii… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Deploying large language models (LLMs) is challenging because they are memory
inefficient and compute-intensive for practical applications. In reaction, researchers train …

Foundational challenges in assuring alignment and safety of large language models

U Anwar, A Saparov, J Rando, D Paleka… - arxiv preprint arxiv …, 2024‏ - arxiv.org
This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems

J Yu, L Lu, X Meng, GE Karniadakis - Computer Methods in Applied …, 2022‏ - Elsevier
Deep learning has been shown to be an effective tool in solving partial differential equations
(PDEs) through physics-informed neural networks (PINNs). PINNs embed the PDE residual …

Explainability of artificial intelligence methods, applications and challenges: A comprehensive survey

W Ding, M Abdel-Basset, H Hawash, AM Ali - Information Sciences, 2022‏ - Elsevier
The continuous advancement of Artificial Intelligence (AI) has been revolutionizing the
strategy of decision-making in different life domains. Regardless of this achievement, AI …

Underspecification presents challenges for credibility in modern machine learning

A D'Amour, K Heller, D Moldovan, B Adlam… - Journal of Machine …, 2022‏ - jmlr.org
Machine learning (ML) systems often exhibit unexpectedly poor behavior when they are
deployed in real-world domains. We identify underspecification in ML pipelines as a key …

Large pre-trained language models contain human-like biases of what is right and wrong to do

P Schramowski, C Turan, N Andersen… - Nature Machine …, 2022‏ - nature.com
Artificial writing is permeating our lives due to recent advances in large-scale, transformer-
based language models (LMs) such as BERT, GPT-2 and GPT-3. Using them as pre-trained …

Explaining deep neural networks and beyond: A review of methods and applications

W Samek, G Montavon, S Lapuschkin… - Proceedings of the …, 2021‏ - ieeexplore.ieee.org
With the broader and highly successful usage of machine learning (ML) in industry and the
sciences, there has been a growing demand for explainable artificial intelligence (XAI) …