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

arXiv:2609.27773v1 Announce Type: cross 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 detection to identify the turns and tokens that push the conversation toward unsafe trajectories. To support this, we construct a multi-turn dataset with behavioral validation and tiered evidence supervision. The dataset contains 1,762 conversations, including adversarial conversations, benign twins, and benign variants with high-risk vocabulary. We train a lightweight hierarchical attribution model that predicts safety violations and attributes them to contributing user turns and token spans. The model achieves strong detection performance (F1=0.988), and removing the top 15% of attributed tokens reduces the adversarial classification confidence by 51.1%. The model preserves low false positive rates on benign conversations with high-risk vocabulary, with false positives below 1% on both borderline benign and benign high-risk vocabulary conversations, compared to 37.3% and 94.7% for a keyword-based surface-risk baseline. Independent human annotation supports the model's attribution performance, with the top-five attributed turns containing a human-identified evidence-bearing turn in 84.5% of adversarial cases.

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 detection to identify the turns and tokens that push the conversation toward unsafe trajectories. To support this, we construct a multi-turn dataset with behavioral validation and tiered evidence supervision. The dataset contains 1,762 conversations, including adversarial conversations, benign twins, and benign variants with high-risk vocabulary. We train a lightweight hierarchical attribution model that predicts safety violations and attributes them to contributing user turns and token spans. The model achieves strong detection performance (F1=0.988), and removing the top 15% of attributed tokens reduces the adversarial classification confidence by 51.1%. The model preserves low false positive rates on benign conversations with high-risk vocabulary, with false positives below 1% on both borderline benign and benign high-risk vocabulary conversations, compared to 37.3% and 94.7% for a keyword-based surface-risk baseline. Independent human annotation supports the model's attribution performance, with the top-five attributed turns containing a human-identified evidence-bearing turn in 84.5% of adversarial cases.

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

arXiv:2609.27773 [cs.CL]

(or arXiv:2609.27773v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.27773 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

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

Related coverage