Innovative Guardrails for Generative AI: Designing an Intelligent Filter for Safe and Responsible LLM Deployment
This paper proposes a technological framework designed to mitigate the inherent risks associated with the deployment of artificial intelligence (AI) in decision-making and task execution within the management processes. The Agreement Validation Interface (AVI) functions as a modular Application Prog...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/13/7298 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849319810601582592 |
|---|---|
| author | Olga Shvetsova Danila Katalshov Sang-Kon Lee |
| author_facet | Olga Shvetsova Danila Katalshov Sang-Kon Lee |
| author_sort | Olga Shvetsova |
| collection | DOAJ |
| description | This paper proposes a technological framework designed to mitigate the inherent risks associated with the deployment of artificial intelligence (AI) in decision-making and task execution within the management processes. The Agreement Validation Interface (AVI) functions as a modular Application Programming Interface (API) Gateway positioned between user applications and LLMs. This gateway architecture is designed to be LLM-agnostic, meaning it can operate with various underlying LLMs without requiring specific modifications for each model. This universality is achieved by standardizing the interface for requests and responses and applying a consistent set of validation and enhancement processes irrespective of the chosen LLM provider, thus offering a consistent governance layer across a diverse LLM ecosystem. AVI facilitates the orchestration of multiple AI subcomponents for input–output validation, response evaluation, and contextual reasoning, thereby enabling real-time, bidirectional filtering of user interactions. A proof-of-concept (PoC) implementation of AVI was developed and rigorously evaluated using industry-standard benchmarks. The system was tested for its effectiveness in mitigating adversarial prompts, reducing toxic outputs, detecting personally identifiable information (PII), and enhancing factual consistency. The results demonstrated that AVI reduced successful fast injection attacks by 82%, decreased toxic content generation by 75%, and achieved high PII detection performance (F1-score ≈ 0.95). Furthermore, the contextual reasoning module significantly improved the neutrality and factual validity of model outputs. Although the integration of AVI introduced a moderate increase in latency, the overall framework effectively enhanced the reliability, safety, and interpretability of LLM-driven applications. AVI provides a scalable and adaptable architectural template for the responsible deployment of generative AI in high-stakes domains such as finance, healthcare, and education, promoting safer and more ethical use of AI technologies. |
| format | Article |
| id | doaj-art-e253ce3b0ee24dd68f279bbac42f4733 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-e253ce3b0ee24dd68f279bbac42f47332025-08-20T03:50:20ZengMDPI AGApplied Sciences2076-34172025-06-011513729810.3390/app15137298Innovative Guardrails for Generative AI: Designing an Intelligent Filter for Safe and Responsible LLM DeploymentOlga Shvetsova0Danila Katalshov1Sang-Kon Lee2School of Industrial Management, Korea University of Technology and Education (KOREATECH), Cheonan-si 31254, Republic of KoreaSchool of Industrial Management, Korea University of Technology and Education (KOREATECH), Cheonan-si 31254, Republic of KoreaSchool of Industrial Management, Korea University of Technology and Education (KOREATECH), Cheonan-si 31254, Republic of KoreaThis paper proposes a technological framework designed to mitigate the inherent risks associated with the deployment of artificial intelligence (AI) in decision-making and task execution within the management processes. The Agreement Validation Interface (AVI) functions as a modular Application Programming Interface (API) Gateway positioned between user applications and LLMs. This gateway architecture is designed to be LLM-agnostic, meaning it can operate with various underlying LLMs without requiring specific modifications for each model. This universality is achieved by standardizing the interface for requests and responses and applying a consistent set of validation and enhancement processes irrespective of the chosen LLM provider, thus offering a consistent governance layer across a diverse LLM ecosystem. AVI facilitates the orchestration of multiple AI subcomponents for input–output validation, response evaluation, and contextual reasoning, thereby enabling real-time, bidirectional filtering of user interactions. A proof-of-concept (PoC) implementation of AVI was developed and rigorously evaluated using industry-standard benchmarks. The system was tested for its effectiveness in mitigating adversarial prompts, reducing toxic outputs, detecting personally identifiable information (PII), and enhancing factual consistency. The results demonstrated that AVI reduced successful fast injection attacks by 82%, decreased toxic content generation by 75%, and achieved high PII detection performance (F1-score ≈ 0.95). Furthermore, the contextual reasoning module significantly improved the neutrality and factual validity of model outputs. Although the integration of AVI introduced a moderate increase in latency, the overall framework effectively enhanced the reliability, safety, and interpretability of LLM-driven applications. AVI provides a scalable and adaptable architectural template for the responsible deployment of generative AI in high-stakes domains such as finance, healthcare, and education, promoting safer and more ethical use of AI technologies.https://www.mdpi.com/2076-3417/15/13/7298generative AIlarge language models (LLMs)AI safetycontent filteringAI ethicsresponsible AI |
| spellingShingle | Olga Shvetsova Danila Katalshov Sang-Kon Lee Innovative Guardrails for Generative AI: Designing an Intelligent Filter for Safe and Responsible LLM Deployment Applied Sciences generative AI large language models (LLMs) AI safety content filtering AI ethics responsible AI |
| title | Innovative Guardrails for Generative AI: Designing an Intelligent Filter for Safe and Responsible LLM Deployment |
| title_full | Innovative Guardrails for Generative AI: Designing an Intelligent Filter for Safe and Responsible LLM Deployment |
| title_fullStr | Innovative Guardrails for Generative AI: Designing an Intelligent Filter for Safe and Responsible LLM Deployment |
| title_full_unstemmed | Innovative Guardrails for Generative AI: Designing an Intelligent Filter for Safe and Responsible LLM Deployment |
| title_short | Innovative Guardrails for Generative AI: Designing an Intelligent Filter for Safe and Responsible LLM Deployment |
| title_sort | innovative guardrails for generative ai designing an intelligent filter for safe and responsible llm deployment |
| topic | generative AI large language models (LLMs) AI safety content filtering AI ethics responsible AI |
| url | https://www.mdpi.com/2076-3417/15/13/7298 |
| work_keys_str_mv | AT olgashvetsova innovativeguardrailsforgenerativeaidesigninganintelligentfilterforsafeandresponsiblellmdeployment AT danilakatalshov innovativeguardrailsforgenerativeaidesigninganintelligentfilterforsafeandresponsiblellmdeployment AT sangkonlee innovativeguardrailsforgenerativeaidesigninganintelligentfilterforsafeandresponsiblellmdeployment |