Explainable AI: current status and future directions

P Gohel, P Singh, M Mohanty - arxiv preprint arxiv:2107.07045, 2021 - arxiv.org
Explainable Artificial Intelligence (XAI) is an emerging area of research in the field of
Artificial Intelligence (AI). XAI can explain how AI obtained a particular solution (eg …

A survey of the state of explainable AI for natural language processing

M Danilevsky, K Qian, R Aharonov, Y Katsis… - arxiv preprint arxiv …, 2020 - arxiv.org
Recent years have seen important advances in the quality of state-of-the-art models, but this
has come at the expense of models becoming less interpretable. This survey presents an …

The fundamentals of Artificial Intelligence in medical education research: AMEE Guide No. 156

MG Tolsgaard, MV Pusic, SS Sebok-Syer, B Gin… - Medical …, 2023 - Taylor & Francis
Abstract The use of Artificial Intelligence (AI) in medical education has the potential to
facilitate complicated tasks and improve efficiency. For example, AI could help automate …

The past, present, and prospective future of xai: A comprehensive review

MU Islam, M Mozaharul Mottalib, M Hassan… - … Artificial Intelligence for …, 2022 - Springer
With the increasing growth and availability of data, Artificial Intelligence (AI) based black-box
models have shown significant effectiveness to solve real-world and mission-critical …

Let's make your request more persuasive: Modeling persuasive strategies via semi-supervised neural nets on crowdfunding platforms

D Yang, J Chen, Z Yang, D Jurafsky… - Proceedings of the 2019 …, 2019 - aclanthology.org
Modeling what makes a request persuasive-eliciting the desired response from a reader-is
critical to the study of propaganda, behavioral economics, and advertising. Yet current …

Uncovering latent biases in text: Method and application to peer review

E Manzoor, NB Shah - Proceedings of the AAAI Conference on Artificial …, 2021 - ojs.aaai.org
Quantifying systematic disparities in numerical quantities such as employment rates and
wages between population subgroups provides compelling evidence for the existence of …

Causal effects of linguistic properties

R Pryzant, D Card, D Jurafsky, V Veitch… - arxiv preprint arxiv …, 2020 - arxiv.org
We consider the problem of using observational data to estimate the causal effects of
linguistic properties. For example, does writing a complaint politely lead to a faster response …

Deep multi-modal structural equations for causal effect estimation with unstructured proxies

S Deshpande, K Wang, D Sreenivas… - Advances in Neural …, 2022 - proceedings.neurips.cc
Estimating the effect of intervention from observational data while accounting for
confounding variables is a key task in causal inference. Oftentimes, the confounders are …

Exploring how feedback reflects entrustment decisions using artificial intelligence

BC Gin, O Ten Cate, PS O'Sullivan, KE Hauer… - Medical …, 2022 - Wiley Online Library
Context Clinical supervisors make judgements about how much to trust learners with critical
activities in patient care. Such decisions mediate trainees' opportunities for learning and …

Riker: Mining rich keyword representations for interpretable product question answering

J Zhao, Z Guan, H Sun - Proceedings of the 25th ACM SIGKDD …, 2019 - dl.acm.org
This work studies product question answering (PQA) which aims to answer product-related
questions based on customer reviews. Most recent PQA approaches adopt end2end …