This is curated repository of resources on bias and machine unlearning in Large Language Models. Its primary purpose is to provide a comprehensive list of relevant resources related to these topics that can support my research and dissertation, under the advisorship of PhD Edna Dias Canedo, in the Professional Graduate Program in Electrical Engineering (PPEE) at the University of Brasília (UnB), Department of Electrical Engineering (ENE).
- Paper List 📃
- Related Awesome Lists 😲
- Toolboxes 🧰
- Seminar ⏰
- Workshops 🔥
- Tutorials 👩🏫
- Talks 🎤
- Blogs ✍️
- Other Resources ✨
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| 2024.08 | D. Bouchard | An actionable framework for assessing bias and fairness in large language model use cases  |
Bias, Evaluation Metrics, Fairness, Framework, Large Language Models, LLMs | arXiv |  |
  |
| 2024.04 | S. Caton and C. Haas | Fairness in machine learning: A survey  |
Fairness, accountability, transparency, machine learning | ACM Comput. Surv. | |
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| 2023.12 | A. F. Oketunji, M. Anas, and D. Saina | Large language model (LLM) bias index - LLMBI  |
Large Language Model, LLM, Model Calibration, Bias Quantification, Bias Mitigation, Algorithmic Fairness, Algorithmic Governance | arXiv | |
|
| 2023.11 | E. Ferrara | Should ChatGPT be biased? Challenges and risks of bias in large language models |
Artificial Intelligence, Generative AI, Bias, Large Language Models, OpenAI, ChatGPT, GPT-3, GPT-4 | First Monday | |
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| 2022.11 | N. Mehrabi, F. Morstatter, N. Saxena, K. Lerman, and A. Galstyan | A survey on bias and fairness in machine learning  |
Fairness and Bias in Artificial Intelligence, Machine Learning, Deep Learning, Natural Language Processing, Representation Learning | ACM Comput. Surv. | |
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| 2024.06 | J. Xu, Z. Wu, C. Wang, and X. Jia | Machine unlearning: Solutions and challenges  |
Machine Unlearning; Machine Learning Security; the Right to be Forgotten | IEEE Trans. Emerg. Top. Comput. Intell. | |
|
| 2024.05 | A. Oesterling, J. Ma, F. P. Calmon, and H. Lakkaraju | Fair machine unlearning: Data removal while mitigating disparities  |
Data Privacy; Fair Machine Learning; Fairness; Machine Unlearning; Right to Be Forgotten | PMLR | |
 |
| 2024.05 | H. Hu, S. Wang, T. Dong, and M. Xue | Learn what you want to unlearn: Unlearning inversion attacks against machine unlearning |
Machine Unlearning, Privacy Vulnerability, Right to be Forgotten, Unlearning Inversion Attacks | SP 2024 | |
 |
| 2024.05 | M. Bertrán, S. Tang, M. Kearns, J. Morgenstern, A. Roth, and Z. S. Wu | Reconstruction attacks on machine unlearning: Simple models are vulnerable  |
Data Privacy, Machine Unlearning, Privacy Risks in AI, Reconstruction Attacks | arXiv | |
|
| 2024.04 | Z. Liu, H. Ye, C. Chen, and K.-Y. Lam | Threats, attacks, and defenses in machine unlearning: A survey  |
Machine unlearning, threats, attacks, defenses | arXiv | |
|
| 2024.03 | N. Li et al. | Machine unlearning: Taxonomy, metrics, applications, challenges, and prospects  |
Machine learning, machine unlearning, data privacy, federated learning | arXiv | |
|
| 2024.03 | J. Foster, S. Schoepf, and A. Brintrup | Fast machine unlearning without retraining through selective synaptic dampening |
Machine Unlearning, Model Performance, Retrain-Free, Selective Synaptic Dampening (SSD) | AAAI 2023 | |
|
| 2024.02 | L. Wang, X. Zeng, J. Guo, K.-F. Wong, and G. Gottlob | Selective forgetting: Advancing machine unlearning techniques and evaluation in language models  |
Machine Unlearning, Language Model, Selective Unlearning | arXiv | |
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| 2023.12 | M. Kurmanji, P. Triantafillou, J. Hayes, and E. Triantafillou | Towards unbounded machine unlearning |
Bias Removal, Machine Unlearning, Model Utility, Right to Be Forgotten, Unlearning Algorithm | NeurIPS 2023 | |
 |
| 2023.08 | H. Xu, T. Zhu, L. Zhang, W. Zhou, and P. S. Yu | Machine Unlearning: A Survey |
Machine learning, deep learning, machine unlearning, sample removal, data privacy, model usabilit | ACM Comput. Surv. | |
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| 2020.06 | Y. Wu, E. Dobriban, and S. B. Davidson | DeltaGrad: Rapid retraining of machine learning models  |
PMLR | |
 |
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| 2024.01 | B. C. Das, M. H. Amini, and Y. Wu | Security and privacy challenges of large language models: A survey  |
Large Language Models, Security and Privacy Challenges, Defense Mechanisms. | arXiv | |
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| 2023.12 | Y. Yao, J. Duan, K. Xu, Y. Cai, E. Sun, and Y. Zhang | A survey on large language model (LLM) security and privacy: The good, the bad, and the ugly  |
Large Language Model (LLM), LLM Security, LLM Privacy, ChatGPT, LLM Attacks, LLM Vulnerabilities | arXiv | |
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
| Date | Author(s) | Title | Keywords | Venue | Bib Source | Code |
|---|---|---|---|---|---|---|
In the context of a research paper, "venue" refers to the specific conference, journal, symposium, or workshop where the paper was published or presented.
| Acronym | Venue |
|---|---|
| AAAI | Association for the Advancement of Artificial IntelligenceSponsorship |
| ACM Comput. Surv. | ACM Computing Surveys |
| IEEE Trans. Emerg. Top. Comput. Intell. | IEEE Transactions on Emerging Topics in Computational Intelligence |
| NeurIPS | Annual Conference on Neural Information Processing Systems |
| PMLR | Proceedings of Machine Learning Research |
| SP | IEEE symposium on security and privacy |
