A secondary warden LLM halves the success rate of hidden-goal adversarial LLMs in steering user decisions while causing only minor interference with genuine interactions.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 5roles
background 3polarities
background 3representative citing papers
Diverse ensembles of prompted and fine-tuned GPT-4.1-Mini monitors achieve 2.4x better detection of flawed code solutions than homogeneous ensembles on adversarial inputs.
LinuxArena is a large-scale control benchmark for AI agents operating in production software environments, with evaluations showing 23% undetected sabotage success for Claude Opus 4.6 against a GPT-5-nano monitor and headroom for future protocols.
The 2025 AI Agent Index catalogs technical and safety details for 30 deployed AI agents and finds low developer transparency on safety, evaluations, and societal impacts.
ATLAS shows constitutions induce recoverable latent geometry in LLMs that redistributes but remains detectable across models and neural perturbation data via source-defined families and AUC separations.
citing papers explorer
-
LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight
A secondary warden LLM halves the success rate of hidden-goal adversarial LLMs in steering user decisions while causing only minor interference with genuine interactions.
-
Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute
Diverse ensembles of prompted and fine-tuned GPT-4.1-Mini monitors achieve 2.4x better detection of flawed code solutions than homogeneous ensembles on adversarial inputs.
-
LinuxArena: A Control Setting for AI Agents in Live Production Software Environments
LinuxArena is a large-scale control benchmark for AI agents operating in production software environments, with evaluations showing 23% undetected sabotage success for Claude Opus 4.6 against a GPT-5-nano monitor and headroom for future protocols.
-
The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems
The 2025 AI Agent Index catalogs technical and safety details for 30 deployed AI agents and finds low developer transparency on safety, evaluations, and societal impacts.
-
ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data
ATLAS shows constitutions induce recoverable latent geometry in LLMs that redistributes but remains detectable across models and neural perturbation data via source-defined families and AUC separations.