Related Experiment Video
Updated: Jun 13, 2025
03:14
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
519
Supporting Trustworthy AI Through Machine Unlearning
Emmie Hine1,2,3, Claudio Novelli4,5, Mariarosaria Taddeo6,7
1Department of Legal Studies, University of Bologna, Via Zamboni, 27/29, 40121, Bologna, Italy. emmie.hine@yale.edu.
Science and Engineering Ethics
|September 11, 2024
Summary
Machine unlearning (MU) supports trustworthy AI principles and the right to be forgotten. However, ethical risks necessitate policy recommendations for responsible research and AI development.
Area of Science:
- Artificial Intelligence
- Machine Learning
- AI Ethics
Background:
- Machine unlearning (MU) is frequently discussed concerning data privacy and the 'right to be forgotten'.
- The Organisation for Economic Co-operation and Development (OECD) principles for trustworthy AI are increasingly influential in global AI governance.
- There is a need to bridge the gap between theoretical AI principles and practical implementation.
Purpose of the Study:
- To demonstrate how machine unlearning can operationalize the OECD's trustworthy AI principles.
- To identify and analyze the ethical risks associated with implementing machine unlearning.
- To propose policy recommendations for fostering responsible MU research and adoption.
Main Methods:
- Conceptual analysis linking machine unlearning capabilities to OECD AI principles.
- Ethical risk assessment of machine unlearning implementation.
- Policy analysis and formulation based on identified risks and benefits.
Main Results:
- Machine unlearning directly supports key OECD principles for trustworthy AI, including fairness, transparency, and accountability.
- The study identifies potential ethical challenges such as unintended data leakage and the complexity of verification.
- A framework of six policy recommendation categories is proposed to guide future MU development.
Conclusions:
- Machine unlearning serves as a practical mechanism for implementing trustworthy AI principles.
- Addressing ethical risks through proactive policy is crucial for maximizing the benefits of machine unlearning.
- The findings provide a foundation for developing regulatory and research agendas for machine unlearning.
Related Concept Videos
01:16Non-equilibrium in the Cell
4.3K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.3K
02:16Stereotype Content Model
14.0K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.0K
01:22Purposive Learning
105
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
105
01:14Avoidance Learning and Learned Helplessness
1.7K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
1.7K