{"ID":2865152,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22041","arxiv_id":"2509.22041","title":"Taxonomy of Comprehensive Safety for Clinical Agents","abstract":"Safety is a paramount concern in clinical chatbot applications, where inaccurate or harmful responses can lead to serious consequences. Existing methods--such as guardrails and tool calling--often fall short in addressing the nuanced demands of the clinical domain. In this paper, we introduce TACOS (TAxonomy of COmprehensive Safety for Clinical Agents), a fine-grained, 21-class taxonomy that integrates safety filtering and tool selection into a single user intent classification step. TACOS is a taxonomy that can cover a wide spectrum of clinical and non-clinical queries, explicitly modeling varying safety thresholds and external tool dependencies. To validate our taxonomy, we curate a TACOS-annotated dataset and perform extensive experiments. Our results demonstrate the value of a new taxonomy specialized for clinical agent settings, and reveal useful insights about train data distribution and pretrained knowledge of base models.","short_abstract":"Safety is a paramount concern in clinical chatbot applications, where inaccurate or harmful responses can lead to serious consequences. Existing methods--such as guardrails and tool calling--often fall short in addressing the nuanced demands of the clinical domain. In this paper, we introduce TACOS (TAxonomy of COmpreh...","url_abs":"https://arxiv.org/abs/2509.22041","url_pdf":"https://arxiv.org/pdf/2509.22041v3","authors":"[\"Jean Seo\",\"Hyunkyung Lee\",\"Gibaeg Kim\",\"Wooseok Han\",\"Jaehyo Yoo\",\"Seungseop Lim\",\"Kihun Shin\",\"Eunho Yang\"]","published":"2025-09-26T08:22:59Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[]","has_code":false}