Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916576726351872 |
|---|---|
| author | Mekala, Anmol Dorna, Vineeth Dubey, Shreya Lalwani, Abhishek Koleczek, David Rungta, Mukund Hasan, Sadid Lobo, Elita |
| author_facet | Mekala, Anmol Dorna, Vineeth Dubey, Shreya Lalwani, Abhishek Koleczek, David Rungta, Mukund Hasan, Sadid Lobo, Elita |
| contents | Machine unlearning aims to efficiently eliminate the influence of specific training data, known as the forget set, from the model. However, existing unlearning methods for Large Language Models (LLMs) face a critical challenge: they rely solely on negative feedback to suppress responses related to the forget set, which often results in nonsensical or inconsistent outputs, diminishing model utility and posing potential privacy risks. To address this limitation, we propose a novel approach called Alternate Preference Optimization (AltPO), which combines negative feedback with in-domain positive feedback on the forget set. Additionally, we introduce new evaluation metrics to assess the quality of responses related to the forget set. Extensive experiments show that our approach not only enables effective unlearning but also avoids undesirable model behaviors while maintaining overall model performance. Our implementation can be found at https://github.com/molereddy/Alternate-Preference-Optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13474 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models Mekala, Anmol Dorna, Vineeth Dubey, Shreya Lalwani, Abhishek Koleczek, David Rungta, Mukund Hasan, Sadid Lobo, Elita Computation and Language Machine Learning Machine unlearning aims to efficiently eliminate the influence of specific training data, known as the forget set, from the model. However, existing unlearning methods for Large Language Models (LLMs) face a critical challenge: they rely solely on negative feedback to suppress responses related to the forget set, which often results in nonsensical or inconsistent outputs, diminishing model utility and posing potential privacy risks. To address this limitation, we propose a novel approach called Alternate Preference Optimization (AltPO), which combines negative feedback with in-domain positive feedback on the forget set. Additionally, we introduce new evaluation metrics to assess the quality of responses related to the forget set. Extensive experiments show that our approach not only enables effective unlearning but also avoids undesirable model behaviors while maintaining overall model performance. Our implementation can be found at https://github.com/molereddy/Alternate-Preference-Optimization. |
| title | Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2409.13474 |