pith. sign in

arxiv: 2412.07724 · v2 · pith:QDCTYHPLnew · submitted 2024-12-10 · 💻 cs.CL

Granite Guardian

Inkit Padhi , Manish Nagireddy , Giandomenico Cornacchia , Subhajit Chaudhury , Tejaswini Pedapati , Pierre Dognin , Keerthiram Murugesan , Erik Miehling
show 15 more authors
Mart\'in Santill\'an Cooper Kieran Fraser Giulio Zizzo Muhammad Zaid Hameed Mark Purcell Michael Desmond Qian Pan Zahra Ashktorab Inge Vejsbjerg Elizabeth M. Daly Michael Hind Werner Geyer Ambrish Rawat Kush R. Varshney Prasanna Sattigeri
This is my paper
classification 💻 cs.CL
keywords graniteguardianmodelsriskacrosscontentdetectionmodel
0
0 comments X
read the original abstract

We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with any large language model (LLM). These models offer comprehensive coverage across multiple risk dimensions, including social bias, profanity, violence, sexual content, unethical behavior, jailbreaking, and hallucination-related risks such as context relevance, groundedness, and answer relevance for retrieval-augmented generation (RAG). Trained on a unique dataset combining human annotations from diverse sources and synthetic data, Granite Guardian models address risks typically overlooked by traditional risk detection models, such as jailbreaks and RAG-specific issues. With AUC scores of 0.871 and 0.854 on harmful content and RAG-hallucination-related benchmarks respectively, Granite Guardian is the most generalizable and competitive model available in the space. Released as open-source, Granite Guardian aims to promote responsible AI development across the community. https://github.com/ibm-granite/granite-guardian

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems

    cs.CR 2026-06 unverdicted novelty 7.0

    BELLS-O is the first vendor-neutral operational benchmark comparing specialized guardrails and repurposed frontier LLMs on accuracy, false-positive rates, speed, and monetary cost across 11 harm categories and 13 jail...

  2. RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration

    cs.CL 2026-04 unverdicted novelty 7.0

    RAGognizer adds a detection head to LLMs for joint training on generation and token-level hallucination detection, yielding SOTA detection and fewer hallucinations in RAG while preserving output quality.

  3. When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models

    cs.LG 2026-04 unverdicted novelty 6.0

    Benign fine-tuning collapses safety geometry in guard models like Granite Guardian, dropping refusal to 0%, but Fisher-Weighted Safety Subspace Regularization restores it to 75% while improving robustness.

  4. Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment

    cs.LG 2025-05 unverdicted novelty 6.0

    Disentangled Safety Adapters decouple safety computations from task-optimized LLMs via lightweight adapters, yielding up to 53% better AUC on safety tasks and dynamic inference-time alignment with reduced performance ...

  5. Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety

    cs.CR 2026-07 unverdicted novelty 5.0

    Cognitive Firewall applies four gates (intent, zero-trust context, consistency, output risk) via an oversight model to cut jailbreak success to 2% or below on most tested sets while keeping over-refusal at 8%.

  6. Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills

    cs.CR 2026-04 unverdicted novelty 5.0

    SkillGuard-Robust formulates pre-load auditing of untrusted Agent Skills as a three-way classification task and achieves 97.30% exact match and 98.33% malicious-risk recall on held-out benchmarks.

  7. Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs

    cs.LG 2026-04 unverdicted novelty 5.0

    Guardian-as-an-Advisor prepends risk labels and explanations from a guardian model to queries, improving LLM safety compliance and reducing over-refusal while adding minimal compute overhead.

  8. Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation

    cs.CL 2026-02 unverdicted novelty 5.0

    Bielik Guard delivers compact Polish safety classifiers with F1 scores near 0.79 and superior real-prompt precision over baselines.

  9. Distilling Safe LLM Systems via Soft Prompts for On Device Settings

    cs.LG 2026-06 unverdicted novelty 4.0

    Soft prompt distillation with total variation and KL divergence transfers safety behaviors from guard models to on-device LLMs and outperforms LoRA adapters, steering vectors, and direct optimization in safety-usefuln...

  10. Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability

    cs.CL 2026-06 unverdicted novelty 4.0

    Fine-tuned LLMs produce incoherent safety responses and yield benchmark-dependent conclusions unless evaluations are grounded in explicit capability targets.

  11. Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content

    cs.LG 2026-05 unverdicted novelty 4.0

    Opir introduces efficient multi-task encoder models trained on a 996-category safety taxonomy that match or exceed larger baselines on most safety benchmarks while using under 100M parameters for edge variants.

  12. TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts

    cs.CR 2026-04 unverdicted novelty 4.0

    TWGuard achieves +0.289 F1 improvement and 94.9% false-positive reduction for LLM safety guardrails in the Taiwan linguistic context compared to foundation models and baselines.