LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912160521650176 |
|---|---|
| author | Elesedy, Hayder Esperança, Pedro M. Oprea, Silviu Vlad Ozay, Mete |
| author_facet | Elesedy, Hayder Esperança, Pedro M. Oprea, Silviu Vlad Ozay, Mete |
| contents | Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for resource-constrained computational portable devices, such as mobile phones, more and more of which are running LLM-based applications locally. We introduce LoRA-Guard, a parameter-efficient guardrail adaptation method that relies on knowledge sharing between LLMs and guardrail models. LoRA-Guard extracts language features from the LLMs and adapts them for the content moderation task using low-rank adapters, while a dual-path design prevents any performance degradation on the generative task. We show that LoRA-Guard outperforms existing approaches with 100-1000x lower parameter overhead while maintaining accuracy, enabling on-device content moderation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_02987 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models Elesedy, Hayder Esperança, Pedro M. Oprea, Silviu Vlad Ozay, Mete Machine Learning Artificial Intelligence Computation and Language Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for resource-constrained computational portable devices, such as mobile phones, more and more of which are running LLM-based applications locally. We introduce LoRA-Guard, a parameter-efficient guardrail adaptation method that relies on knowledge sharing between LLMs and guardrail models. LoRA-Guard extracts language features from the LLMs and adapts them for the content moderation task using low-rank adapters, while a dual-path design prevents any performance degradation on the generative task. We show that LoRA-Guard outperforms existing approaches with 100-1000x lower parameter overhead while maintaining accuracy, enabling on-device content moderation. |
| title | LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2407.02987 |