paper-with-me

홈 › Papers

Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

2023-12-07 · Hakan Inan, Kartikeya Upasani, Jianfeng Chi, Rashi Rungta, Krithika Iyer, Yuning Mao, Michael Tontchev, Qing Hu, Brian Fuller, Davide Testuggine, Madian Khabsa

We introduce Llama Guard, an LLM-based input-output safeguard model geared towards Human-AI conversation use cases. Our model incorporates a safety risk taxonomy, a valuable tool for categorizing a specific set of safety risks found in LLM prompts (i.e., prompt classification). This taxonomy is also instrumental in classifying the responses generated by LLMs to these prompts, a process we refer to as response classification. For the purpose of both prompt and response classification, we have meticulously gathered a dataset of high quality. Llama Guard, a Llama2-7b model that is instruction-tuned on our collected dataset, albeit low in volume, demonstrates strong performance on existing benchmarks such as the OpenAI Moderation Evaluation dataset and ToxicChat, where its performance matches or exceeds that of currently available content moderation tools. Llama Guard functions as a language model, carrying out multi-class classification and generating binary decision scores. Furthermore, the instruction fine-tuning of Llama Guard allows for the customization of tasks and the adaptation of output formats. This feature enhances the model's capabilities, such as enabling the adjustment of taxonomy categories to align with specific use cases, and facilitating zero-shot or few-shot prompting with diverse taxonomies at the input. We are making Llama Guard model weights available and we encourage researchers to further develop and adapt them to meet the evolving needs of the community for AI safety.

📄 PDF Abstract BibTeX arXiv:2312.06674

Code (1)

lastmile-ai/aiconfig/tree/main/cookbooks/LLaMA-Guard

Tasks

ClassificationLanguage ModellingMulti-class Classification

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

2024-11-15 · Jianfeng Chi, Ujjwal Karn, Hongyuan Zhan, Eric Smith 외

We introduce Llama Guard 3 Vision, a multimodal LLM-based safeguard for human-AI conversations that involves image understanding: it can be used to safeguard content for both multimodal LLM inputs (prompt classification)…

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

2024-11-18 · Igor Fedorov, Kate Plawiak, Lemeng Wu, Tarek Elgamal 외

This paper presents Llama Guard 3-1B-INT4, a compact and efficient Llama Guard model, which has been open-sourced to the community during Meta Connect 2024. We demonstrate that Llama Guard 3-1B-INT4 can be deployed on re…

CPU

Building Guardrails for Large Language Models

2024-02-02 · Yi Dong, Ronghui Mu, Gaojie Jin, Yi Qi 외

As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts on human users and societies. Guardrail…

Taxonomy-Adaptive Moderation Model with Robust Guardrails for Large Language Models

2025-12-05 · Mahesh Kumar Nandwana, Youngwan Lim, Joseph Liu, Alex Yang 외 arxiv

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores …

Decision Making

BELLS: A Framework Towards Future Proof Benchmarks for the Evaluation of LLM Safeguards

2024-06-03 · Diego Dorn, Alexandre Variengien, Charbel-Raphaël Segerie, Vincent Corruble

Input-output safeguards are used to detect anomalies in the traces produced by Large Language Models (LLMs) systems. These detectors are at the core of diverse safety-critical applications such as real-time monitoring, o…