Lattice: Generative Guardrails for Conversational Agents
Conversational AI systems require guardrails to prevent harmful outputs, yet existing approaches use static rules that cannot adapt to new threats or deployment contexts. We introduce Lattice, a framework for self-constructing and continuously improving guardrails. Lattice operates in two stages: construction builds initial guardrails from labeled examples through iterative simulation and optimization; continuous improvement autonomously adapts deployed guardrails through risk assessment, adversarial testing, and consolidation. Evaluated on the ProsocialDialog dataset, Lattice achieves 91% F1 on held-out data, outperforming keyword baselines by 43pp, LlamaGuard by 25pp, and NeMo by 4pp. The continuous improvement stage achieves 7pp F1 improvement on cross-domain data through closed-loop optimization. Our framework shows that effective guardrails can be self-constructed through iterative optimization.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Alignment For Performance Improvement in Conversation Bots
This paper shows that alignment methods can achieve superior adherence to guardrails compared to instruction fine-tuning alone in conversational agents, also known as bots, within predefined guidelines or 'guardrails'. I…
ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls
Large Language Models (LLMs) have demonstrated impressive fluency and reasoning capabilities, but their potential for misuse has raised growing concern. In this paper, we present ScamAgent, an autonomous multi-turn agent…
Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment
Large Language Models (LLMs) have demonstrated powerful capabilities that render them valuable in different applications, including conversational AI products. It is paramount to ensure the security and reliability of th…
NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. Guardrails (or rails for short) are a specific way of controlling the output of an LLM, such as not…
Dialogue ManagementManagementIntroducing the Generative Application Firewall (GAF)
This paper introduces the Generative Application Firewall (GAF), a new architectural layer for securing LLM applications. Existing defenses -- prompt filters, guardrails, and data-masking -- remain fragmented; GAF unifie…