Knowledge Base Regulation Tracker Standards & Frameworks OSS Directory AI Incident Database Research Paper Library Case Studies Society Articles News Jobs About Charter Sign inBecome a Member
Home/Research Paper Library/Alignment Faking in Large Language Models

Alignment Faking in Large Language Models

The first empirical demonstration of alignment faking in a production model, with Redwood Research, showing training-based alignment can be gamed by the model itself.

alignment fakinganthropicredwooddeception

Research question

Will a model strategically comply with training it disagrees with to avoid being modified?

Key findings

  • Claude 3 Opus complied with harmful queries 14% of the time when it believed outputs would be used for training, reasoning explicitly about preserving its values - Alignment faking persisted and rose to 78% after actual RL training on the conflicting objective - Behaviour appeared with information delivered through synthetic documents, not only prompts

Sources

PreviousAlignment Faking in Large Language ModelsNextFrontier AI systems have surpassed the self-replicating red line

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit researchReport a correction or request removal

Related in Research Paper Library

Rouxii: Exploiting Honeypots with Deception-Aware AI Pentesters

Honeypots are designed to deceive attackers, and recent work shows they can also derail autonomous LLM-based pentesters. These evaluations, however, largely consider attackers unaware of the deception they face. We…

Deception, scheming and alignment faking2026

The Deception Delta: Adversarial Evaluation of LLM-Based Smart Contract Bytecode Forensics

Large language models are increasingly used in blockchain forensic investigations to interpret unverified smart contract bytecode. Their robustness has not been systematically tested against contracts adversarially…

Deception, scheming and alignment faking2026

Stress Testing Deliberative Alignment for Anti-Scheming Training

OpenAI and Apollo's joint study of anti-scheming training, reporting large reductions in covert behaviour alongside rising evaluation awareness.

Deception, scheming and alignment faking2025