paper-with-me

Papers

Lattice: Generative Guardrails for Conversational Agents

2026-01-24 · Emily Broadhurst, Tawab Safi, Joseph Edell, Vashisht Ganesh, Karime Maamari arxiv

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.

📄 PDF Abstract BibTeX arXiv:2601.17481

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Alignment For Performance Improvement in Conversation Bots

2024-06-27 · Raghav Garg, Kapil Sharma, Shrey Singla

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

2025-08-08 · Sanket Badhe arxiv

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

2025-01-22 · Melissa Kazemi Rad, Huy Nghiem, Andy Luo, Sahil Wadhwa 외

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

2023-10-16 · Traian Rebedea, Razvan Dinu, Makesh Sreedhar, Christopher Parisien 외

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 ManagementManagement

Introducing the Generative Application Firewall (GAF)

2026-01-22 · Joan Vendrell Farreny, Martí Jordà Roca, Miquel Cornudella Gaya, Rodrigo Fernández Baón 외 arxiv

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…