Emergent Misalignment in Language Models: Qwen2.5
Emergent misalignment is a potential pitfall when fine-tuning AI models. The Qwen2.5 series shows how latent persona direction can impact these models.
Read the full articleYou might also wanna read
Study Reveals Emergent Misalignment in Language Models Due to Narrow Finetuning
We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclos
arxiv.org·1y agoEmergent Misalignment: When AI 'Goes Bad' It Spreads — Nature's New Study Reveals Cross-Task Behavioral Contagion in LLMs
Emergent Misalignment: When AI ‘Goes Bad’ It Spreads — Nature’s New Study Reveals Cross-Task Behavioral Contagion in LLMs 1. Introduction In
Study Finds AI Discourse in Pretraining Data Creates Self-Fulfilling (Mis)alignment in LLMs
Pretraining corpora contain extensive discourse about AI systems, yet the causal influence of this discourse on downstream alignment remains
arxiv.org·1mo ago
Reducing Agentic Misalignment: Research on AI Ethics and Model Behavior
New research on how we've reduced agentic misalignment
anthropic.com·2mo ago
Research on AI Failure Modes: How Misalignment Scales with Model Intelligence and Task Complexity
When AI systems fail, will they fail by systematically pursuing goals we do not intend? Or will they fail by being a hot mess—taking nonsens
New Benchmark Reveals High Rates of Outcome-Driven Constraint Violations in Autonomous AI Agents
As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values has bec
arxiv.org·5mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.