Advancing AI Fairness, Safety, and Responsibility
I’m a third-year PhD student at the McCombs School of Business Information, Risk, and Operations Management (IROM) Department. I’m fortunate to be advised by Maria De-Arteaga and Maytal Saar-Tsechansky.
My research advances fairness, safety, and responsibility in the development and use of artificial intelligence (AI) systems trained to replicate human opinions, judgments, and values. As such, it is very interdisciplinary and involves auditing contemporary AI and NLP systems with theoretical lenses from the social sciences, complex systems, and ethics.
Ethics of Automating Human Judgments
One promise of AI rests on its ability to automate decision-making tasks that have traditionally relied on human judgment, especially in areas where a clear-cut ground truth is often lacking (e.g., determining whether content is harmful). However, human judgments are inherently subject to biases, underscoring the importance of carefully analyzing which biases AI systems may reflect in their output. My work focuses on identifying and addressing the implications of such biases, particularly within the realm of AI-assisted fact-checking.
In this domain, I have formulated ethical frameworks to evaluate potential harms arising from AI usage, assessed the fairness of models used to prioritize content for fact-checking in simulated social networks, and investigated the capacity of large language models (LLMs) to represent diverse viewpoints on contentious issues.
AI Alignment and Governance Research
Additionally, I am interested in developing technical approaches for AI alignment with human values, as well as governance approaches to safely open-source advanced AI.
In the technical domain, I plan to initiate research on “supervisor” models designed to detect deception in LLMs. These supervisor models could serve as a crucial layer of oversight, identifying and mitigating instances where LLMs might generate misleading, manipulative, or otherwise unsafe content.
On the governance side, I am interested in crafting policies and technical standards that facilitate the safe sharing of advanced AI technologies, ensuring they cannot be used for nefarious purposes. For instance, I propose “locking” inference for models that have been additionally trained after initial distribution until red-teaming evaluations are passed.
Publications
2023
Neumann, Terrence, and Nicholas Wolczynski. “Does AI-Assisted Fact-Checking Disproportionately Benefit Majority Groups Online?.” Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency. 2023. pdf
Tanriverdi, Hüseyin, John-Patrick Akinyemi, and Terrence Neumann. “Mitigating Bias in Organizational Development and Use of Artificial Intelligence.” Proceedings of the 2023 AIS International Conference on Information Systems. 2023. pdf
2022
Neumann, Terrence, Maria De-Arteaga, and Sina Fazelpour. “Justice in misinformation detection systems: An analysis of algorithms, stakeholders, and potential harms.” Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency. 2022. pdf
Working Papers
Diverse, but Divisive: LLMs Can Exaggerate Differences in Opinion Related to Harms of Misinformation. With Sooyong Lee, Maria De-Arteaga, Sina Fazelpour, and Matt Lease. pdf
How Can Artificial General Intelligence Be Open-Sourced Safely? With Bryan Jones. Draft forthcoming.
About Me
In my spare time, I like to run around Austin (currently training for an ultra-marathon!), watch movies at AFS, and experiment with my ever growing guitar pedal collection.