Safeguarding Large Language Models: A Survey
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_ | 1866909217106952192 |
|---|---|
| author | Dong, Yi Mu, Ronghui Zhang, Yanghao Sun, Siqi Zhang, Tianle Wu, Changshun Jin, Gaojie Qi, Yi Hu, Jinwei Meng, Jie Bensalem, Saddek Huang, Xiaowei |
| author_facet | Dong, Yi Mu, Ronghui Zhang, Yanghao Sun, Siqi Zhang, Tianle Wu, Changshun Jin, Gaojie Qi, Yi Hu, Jinwei Meng, Jie Bensalem, Saddek Huang, Xiaowei |
| contents | In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This article provides a systematic literature review on the current status of this critical mechanism. It discusses its major challenges and how it can be enhanced into a comprehensive mechanism dealing with ethical issues in various contexts. First, the paper elucidates the current landscape of safeguarding mechanisms that major LLM service providers and the open-source community employ. This is followed by the techniques to evaluate, analyze, and enhance some (un)desirable properties that a guardrail might want to enforce, such as hallucinations, fairness, privacy, and so on. Based on them, we review techniques to circumvent these controls (i.e., attacks), to defend the attacks, and to reinforce the guardrails. While the techniques mentioned above represent the current status and the active research trends, we also discuss several challenges that cannot be easily dealt with by the methods and present our vision on how to implement a comprehensive guardrail through the full consideration of multi-disciplinary approach, neural-symbolic method, and systems development lifecycle. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_02622 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Safeguarding Large Language Models: A Survey Dong, Yi Mu, Ronghui Zhang, Yanghao Sun, Siqi Zhang, Tianle Wu, Changshun Jin, Gaojie Qi, Yi Hu, Jinwei Meng, Jie Bensalem, Saddek Huang, Xiaowei Cryptography and Security Artificial Intelligence In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This article provides a systematic literature review on the current status of this critical mechanism. It discusses its major challenges and how it can be enhanced into a comprehensive mechanism dealing with ethical issues in various contexts. First, the paper elucidates the current landscape of safeguarding mechanisms that major LLM service providers and the open-source community employ. This is followed by the techniques to evaluate, analyze, and enhance some (un)desirable properties that a guardrail might want to enforce, such as hallucinations, fairness, privacy, and so on. Based on them, we review techniques to circumvent these controls (i.e., attacks), to defend the attacks, and to reinforce the guardrails. While the techniques mentioned above represent the current status and the active research trends, we also discuss several challenges that cannot be easily dealt with by the methods and present our vision on how to implement a comprehensive guardrail through the full consideration of multi-disciplinary approach, neural-symbolic method, and systems development lifecycle. |
| title | Safeguarding Large Language Models: A Survey |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2406.02622 |