跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+758新增论文
+578其中 AI 相关
+94已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 06:27 — 2026-11-17 06:27(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-17 04:58最近发现新增版本:2026-11-17 04:58库内论文最新更新时间:2026-11-14 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

24,106 已收录论文20,158 AI 相关7,049 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 1 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.748ACL Anthology · ACL 2026

Domain Generalizable AI Guardrails with Augmented Policy Training

Minqian Liu, Ioana Baldini Bloomberg, David Rabinowitz Bloomberg, David S Rosenberg Bloomberg, Sebastian Gehrmann Bloomberg, Mark Dredze Department of Computer Science, Whiting School of Engineering and Bloomberg

原文摘要

AI guardrail systems support usage policies by determining whether a user query or a generated response is allowed or forbidden under the policy. Fine-tuned guardrails – such as LlamaGuard and ShieldGemma – include policy definitions in prompts during training that can be updated during inference to aid generalization. However, our analysis reveals that these models still overfit the training policies, which prevents adaptation to new domains. We propose Augmented Policy Training (APT), a training recipe that enhances guardrail adaptability to unseen policies by using a suite of policy perturbation strategies during training to reduce overfitting and increase generalization. Notably, a small 1B model trained in this manner achieves comparable or better performance than existing 8B guardrails on unseen policies. Our work reveals critical limitations of existing AI guardrails, offers a promising solution, and provides actionable insights for adapting systems to new domains and policies.

cs.CL

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表