conftrace_

safety detection

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (5) explainable ai (2) adversarial benchmark (1) customizable detection (1) task-specific risk (1) explainable safety (1) contextual judge (1) llm agent safety (1) adaptive safety detection (1) lifelong guardrail (1)

Papers

Code-Switching as a Safety Failure Mode in Large Language Models: An Empirical Study of Roman Urdu across English, Mixed, and Transliteration-Only Inputs EACL 2026 OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows ACL 2026 Reasoning’s Razor: Reasoning Improves Accuracy but Hurts Recall at Critical Operating Points in Safety and Hallucination Detection EACL 2026 AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection ACL 2025 ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors EMNLP 2024 InstructSafety: A Unified Framework for Building Multidimensional and Explainable Safety Detector through Instruction Tuning EMNLP 2023