_
RobertoLofaro.com - Knowledge Portal
Change, with and without technology
for updates on publications, follow @changerulebook on either Instagram or Twitter - you can also support on Patreon or subscribe on YouTube


_

You are now here: AI Ethics Primer - search within the bibliography - version 0.3 of 2023-08-13 > (tag cloud) >tag_selected: experiments

Selected tag: experiments

The AI Index 2022 Annual Report / 2205.03468 / on (web) Publishing site
Report highlights
Chapter 3 Technical AI Ethics


ESR: Ethics and Society Review of Artificial Intelligence Research / 2106.11521 / on (web) Publishing site
4 Deployment and Evaluation
A Appendix: Interview Protocol


GPT detectors are biased against non-native English writers / 2304.02819 / on (web) Publishing site
Materials and Methods


Regulating AI manipulation: Applying Insights from behavioral economics and psychology to enhance the practicality of the EU AI Act / 2308.02041 / on (web) Publishing site
2 Clarifying Terminologies of Article-5: Insights from Behavioral Economics and Psychology
3 Enhancing Protection for the General Public and Vulnerable Groups
4 Conclusion


A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation / 2305.11391 / on (web) Publishing site
2 Large Language Models
Reference


Getting pwn'd by AI: Penetration Testing with Large Language Models / 2308.00121 / on (web) Publishing site
1 Introduction


Targeted Data Augmentation for bias mitigation / 2308.11386 / on (web) Publishing site
1 Introduction
4 Experiments
5 Conclusions


Collect, Measure, Repeat: Reliability Factors for Responsible AI Data Collection / 2308.12885 / on (web) Publishing site
2 Related Work on Data Excellence
3 Reliability and Reproducibility Metrics for Responsible Data Collection
4 Published Annotation Tasks and Datasets
5 Results
6 Discussion
7 Conclusions
References
B Variability Analysis
C Power analysis


The Promise and Peril of Artificial Intelligence -- Violet Teaming Offers a Balanced Path Forward / 2308.14253 / on (web) Publishing site
References


Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories? / 2308.15399 / on (web) Publishing site
Abstract
1 Introduction
4 Experiment
References
Ethical statement


Ethical Framework for Harnessing the Power of AI in Healthcare and Beyond / 2309.00064 / on (web) Publishing site
2 Black box and lack of transparency