Building Guardrails for Large Language Models
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. Guardrails, which filter the inputs or outputs of LLMs, have emerged as a core safeguarding technology. This position paper takes a deep look at current open-source solutions (Llama Guard, Nvidia NeMo, Guardrails AI), and discusses the challenges and the road towards building more complete solutions. Drawing on robust evidence from previous research, we advocate for a systematic approach to construct guardrails for LLMs, based on comprehensive consideration of diverse contexts across various LLMs applications. We propose employing socio-technical methods through collaboration with a multi-disciplinary team to pinpoint precise technical requirements, exploring advanced neural-symbolic implementations to embrace the complexity of the requirements, and developing verification and testing to ensure the utmost quality of the final product.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Triaging Threats to Specialized Guardrails
Building robust safety guardrails is essential for deploying Large Language Models across diverse real-world applications. However, this goal remains challenging because safety risks span heterogeneous threat domains, wh…
Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
Recent advancements in large language models (LLMs) have underscored their vulnerability to safety alignment jailbreaks, particularly when subjected to downstream fine-tuning. However, existing mitigation strategies prim…
Safety AlignmentOmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning
Omni-modal Large Language Models (OLLMs) that process text, images, videos, and audio introduce new challenges for safety and value guardrails in human-AI interaction. Prior guardrail research largely targets unimodal se…
Binary ClassificationBreaking Guardrails, Facing Walls: Insights on Adversarial AI for Defenders & Researchers
Analyzing 500 CTF participants, this paper shows that while participants readily bypassed simple AI guardrails using common techniques, layered multi-step defenses still posed significant challenges, offering concrete in…
Benchmarking LLM Guardrails in Handling Multilingual Toxicity
With the ubiquity of Large Language Models (LLMs), guardrails have become crucial to detect and defend against toxic content. However, with the increasing pervasiveness of LLMs in multilingual scenarios, their effectiven…
Benchmarking