State-Dependent Safety Failures in Multi-Turn Language Model Interaction
Quick summary
arXiv:2603.15684v2 Announce Type: replace-cross Abstract: Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically effective, the structure of conversational safety failure remains insufficiently understood. In this work, we study safety failures from a state-space perspective and show that many multi-turn safety failures in current safety-aligned language models arise from contextual state evolution, a regime that is not fully captured by isolated prompt-level analyses a
Key takeaways
- arXiv:2603.15684v2 Announce Type: replace-cross Abstract: Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn.
- Although multi-turn jailbreaks are empirically effective, the structure of conversational safety failure remains insufficiently understood.
- In this work, we study safety failures from a state-space perspective and show that many multi-turn safety failures in current safety-aligned language models arise from contextual state evolution, a regime that is not fully captured by isolated prompt-level analyses a
Why it matters
“State-Dependent Safety Failures in Multi-Turn Language Model Interaction” shows why AI risk cannot be reduced to answer accuracy. Access controls, logging, human approval and incident response need to be designed into the workflow from the start.