_
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: inference

Selected tag: inference

The AI Index 2022 Annual Report / 2205.03468 / on (web) Publishing site
Report highlights
Chapter 2 Technical Performance
Chapter 3 Technical AI Ethics
Appendix


Exciting, Useful, Worrying, Futuristic: Public Perception of Artificial Intelligence in 8 Countries / 2001.00081 / on (web) Publishing site
References


Worldwide AI Ethics: a review of 200 guidelines and recommendations for AI governance / 2206.11922 / on (web) Publishing site
4 Results
References


On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial Services / 2111.01306 / on (web) Publishing site
3 Practical Challengesof Ethical AI


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


Normative Ethics Principles for Responsible AI Systems: Taxonomy and Future Directions / 2208.12616 / on (web) Publishing site
4 Previous operationalisation of ethical principles


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
3 Vulnerabilities, Attack, and Limitations
6 Verification
7 Runtime Monitor
Reference


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


Targeted Data Augmentation for bias mitigation / 2308.11386 / on (web) Publishing site
2 Related works


Building Trust in Conversational AI: A Comprehensive Review and Solution Architecture for Explainable, Privacy-Aware Systems using LLMs and Knowledge Graph / 2308.13534 / on (web) Publishing site
VI. Solution architecture for privacy-aware and trustworthy conversational AI


The Promise and Peril of Artificial Intelligence -- Violet Teaming Offers a Balanced Path Forward / 2308.14253 / on (web) Publishing site
7 Violet teaming to address dual-use risks of AI in biotechnology


The AI Revolution: Opportunities and Challenges for the Finance Sector / 2308.16538 / on (web) Publishing site
2 Key AI technology in financial services


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
References