Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.08142 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909489284775936 |
|---|---|
| author | Han, Shanshan Avestimehr, Salman He, Chaoyang |
| author_facet | Han, Shanshan Avestimehr, Salman He, Chaoyang |
| contents | We present Wildflare GuardRail, a guardrail pipeline designed to enhance the safety and reliability of Large Language Model (LLM) inferences by systematically addressing risks across the entire processing workflow. Wildflare GuardRail integrates several core functional modules, including Safety Detector that identifies unsafe inputs and detects hallucinations in model outputs while generating root-cause explanations, Grounding that contextualizes user queries with information retrieved from vector databases, Customizer that adjusts outputs in real time using lightweight, rule-based wrappers, and Repairer that corrects erroneous LLM outputs using hallucination explanations provided by Safety Detector. Results show that our unsafe content detection model in Safety Detector achieves comparable performance with OpenAI API, though trained on a small dataset constructed with several public datasets. Meanwhile, the lightweight wrappers can address malicious URLs in model outputs in 1.06s per query with 100% accuracy without costly model calls. Moreover, the hallucination fixing model demonstrates effectiveness in reducing hallucinations with an accuracy of 80.7%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_08142 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bridging the Safety Gap: A Guardrail Pipeline for Trustworthy LLM Inferences Han, Shanshan Avestimehr, Salman He, Chaoyang Artificial Intelligence We present Wildflare GuardRail, a guardrail pipeline designed to enhance the safety and reliability of Large Language Model (LLM) inferences by systematically addressing risks across the entire processing workflow. Wildflare GuardRail integrates several core functional modules, including Safety Detector that identifies unsafe inputs and detects hallucinations in model outputs while generating root-cause explanations, Grounding that contextualizes user queries with information retrieved from vector databases, Customizer that adjusts outputs in real time using lightweight, rule-based wrappers, and Repairer that corrects erroneous LLM outputs using hallucination explanations provided by Safety Detector. Results show that our unsafe content detection model in Safety Detector achieves comparable performance with OpenAI API, though trained on a small dataset constructed with several public datasets. Meanwhile, the lightweight wrappers can address malicious URLs in model outputs in 1.06s per query with 100% accuracy without costly model calls. Moreover, the hallucination fixing model demonstrates effectiveness in reducing hallucinations with an accuracy of 80.7%. |
| title | Bridging the Safety Gap: A Guardrail Pipeline for Trustworthy LLM Inferences |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2502.08142 |