AprielGuard
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909980846718976 |
|---|---|
| author | Kasundra, Jaykumar Praharaj, Anjaneya Surana, Sourabh Chodisetty, Lakshmi Sirisha Sharma, Sourav Verma, Abhigya Bhardwaj, Abhishek Kanhar, Debasish Bhagat, Aakash Slimi, Khalil Subramanian, Seganrasan Madhusudhan, Sathwik Tejaswi Chenna, Ranga Prasad Sunkara, Srinivas |
| author_facet | Kasundra, Jaykumar Praharaj, Anjaneya Surana, Sourabh Chodisetty, Lakshmi Sirisha Sharma, Sourav Verma, Abhigya Bhardwaj, Abhishek Kanhar, Debasish Bhagat, Aakash Slimi, Khalil Subramanian, Seganrasan Madhusudhan, Sathwik Tejaswi Chenna, Ranga Prasad Sunkara, Srinivas |
| contents | Safeguarding large language models (LLMs) against unsafe or adversarial behavior is critical as they are increasingly deployed in conversational and agentic settings. Existing moderation tools often treat safety risks (e.g. toxicity, bias) and adversarial threats (e.g. prompt injections, jailbreaks) as separate problems, limiting their robustness and generalizability. We introduce AprielGuard, an 8B parameter safeguard model that unify these dimensions within a single taxonomy and learning framework. AprielGuard is trained on a diverse mix of open and synthetic data covering standalone prompts, multi-turn conversations, and agentic workflows, augmented with structured reasoning traces to improve interpretability. Across multiple public and proprietary benchmarks, AprielGuard achieves strong performance in detecting harmful content and adversarial manipulations, outperforming existing opensource guardrails such as Llama-Guard and Granite Guardian, particularly in multi-step and reasoning intensive scenarios. By releasing the model, we aim to advance transparent and reproducible research on reliable safeguards for LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_20293 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AprielGuard Kasundra, Jaykumar Praharaj, Anjaneya Surana, Sourabh Chodisetty, Lakshmi Sirisha Sharma, Sourav Verma, Abhigya Bhardwaj, Abhishek Kanhar, Debasish Bhagat, Aakash Slimi, Khalil Subramanian, Seganrasan Madhusudhan, Sathwik Tejaswi Chenna, Ranga Prasad Sunkara, Srinivas Computation and Language Safeguarding large language models (LLMs) against unsafe or adversarial behavior is critical as they are increasingly deployed in conversational and agentic settings. Existing moderation tools often treat safety risks (e.g. toxicity, bias) and adversarial threats (e.g. prompt injections, jailbreaks) as separate problems, limiting their robustness and generalizability. We introduce AprielGuard, an 8B parameter safeguard model that unify these dimensions within a single taxonomy and learning framework. AprielGuard is trained on a diverse mix of open and synthetic data covering standalone prompts, multi-turn conversations, and agentic workflows, augmented with structured reasoning traces to improve interpretability. Across multiple public and proprietary benchmarks, AprielGuard achieves strong performance in detecting harmful content and adversarial manipulations, outperforming existing opensource guardrails such as Llama-Guard and Granite Guardian, particularly in multi-step and reasoning intensive scenarios. By releasing the model, we aim to advance transparent and reproducible research on reliable safeguards for LLMs. |
| title | AprielGuard |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2512.20293 |