LLMGuard: Guarding Against Unsafe LLM Behavior
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910350190837760 |
|---|---|
| author | Goyal, Shubh Hira, Medha Mishra, Shubham Goyal, Sukriti Goel, Arnav Dadu, Niharika DB, Kirushikesh Mehta, Sameep Madaan, Nishtha |
| author_facet | Goyal, Shubh Hira, Medha Mishra, Shubham Goyal, Sukriti Goel, Arnav Dadu, Niharika DB, Kirushikesh Mehta, Sameep Madaan, Nishtha |
| contents | Although the rise of Large Language Models (LLMs) in enterprise settings brings new opportunities and capabilities, it also brings challenges, such as the risk of generating inappropriate, biased, or misleading content that violates regulations and can have legal concerns. To alleviate this, we present "LLMGuard", a tool that monitors user interactions with an LLM application and flags content against specific behaviours or conversation topics. To do this robustly, LLMGuard employs an ensemble of detectors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_00826 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLMGuard: Guarding Against Unsafe LLM Behavior Goyal, Shubh Hira, Medha Mishra, Shubham Goyal, Sukriti Goel, Arnav Dadu, Niharika DB, Kirushikesh Mehta, Sameep Madaan, Nishtha Computation and Language Cryptography and Security Machine Learning Although the rise of Large Language Models (LLMs) in enterprise settings brings new opportunities and capabilities, it also brings challenges, such as the risk of generating inappropriate, biased, or misleading content that violates regulations and can have legal concerns. To alleviate this, we present "LLMGuard", a tool that monitors user interactions with an LLM application and flags content against specific behaviours or conversation topics. To do this robustly, LLMGuard employs an ensemble of detectors. |
| title | LLMGuard: Guarding Against Unsafe LLM Behavior |
| topic | Computation and Language Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2403.00826 |