Beyond Unsafe Detection: Counterfactually Anchored Evidence Attribution for Multi-Turn LLM Safety Failures

Excerpt

arXiv:2609.27773v1 Announce Type: new Abstract: As Large Language Models (LLMs) move from conversational assistants to advanced agentic systems, guardrail failures can convert adversarial intents into harmful executions. However, most guardrail evaluation frameworks focus only on the result and assess whether a user request is safe or unsafe. This approach is insufficient for multi-turn failures, where adversarial intent is distributed across multiple turns. This motivates us to go beyond detect