Model Detail
Prompt-Guard-86M
—Prompt-Guard-86M is a large language model with 139M parameters released by Meta. The model is registered under the text-classification pipeline tag on Hugging Face, released under the llama3.1 license.
Prompt-Guard-86M ships with 139M parameters. Access is gated on Hugging Face under the llama3.1 license, which means a manual approval step before weights can be downloaded.
Prompt-Guard-86M is best fit for general-purpose chat and instruction-following workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Context-Aware Prompt Injection Detection via Small Language Models in RAG Pipelines: nokast-secureRAG
arXiv:2610.28364v1 Announce Type: cross Abstract: Local Retrieval-Augmented Generation (RAG) systems are vulnerable to indirect prompt injection and retrieval poisoning, where malicious instructions in retrieved content are mistaken for trusted input. We present nokast-secureRAG, a roughly 0.5B-para
Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
arXiv:2605.10765v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, yet real-world deployment often requires continual capability expansion across sequential tasks. In such scenarios, Multimodal Continual Instructi
Beyond the Prompt: Recovering Hidden Concepts in Text-to-Image Models
arXiv:2610.27473v1 Announce Type: cross Abstract: Text-to-image models can generate visual concepts that their prompts never mention, and recent work shows that such associations can be implanted so that ordinary prompts trigger them. Auditing this behavior requires recovering the description that a
Explore More, Validate Less: Efficient Reflective Prompt Optimization
arXiv:2610.27367v1 Announce Type: new Abstract: Reflective prompt optimization improves instructions using task feedback, but coupling candidate generation with full-validation-based selection can make search costly and sequential. We propose a two-stage framework that decouples reflective candidate
The Complexity Kink: A Prompt-Side Structural Complexity Index for Code-Generation Reliability
arXiv:2609.19616v4 Announce Type: replace Abstract: Measuring complexity from a model's own code is biased by failure: a hard prompt can produce a short, broken program that looks simple. We instead score each prompt's structure on six dimensions from the prompt alone, never from generated code or t
Training-Free Continual Learning for Multimodal Forecasting via Prompt Evolution
arXiv:2610.27468v1 Announce Type: cross Abstract: Adapting a forecasting system to a changing world classically means retraining. We ask whether the task of continually learning regimes for time series forecasting can be represented by a piece of text: a guidance block, evolved by outcome-driven ref
