{"paper":{"title":"SAFE-Teen: Evaluating Chatbot Safety Across Adolescent Mental Health Conversations","arxiv_id":"2611.07218","primary_cat":"cs.CL","submitted_at":"2026-11-04T23:11:33+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"Adolescents are increasingly turning to AI chatbots for mental health support, advice, and companionship, raising safety concerns.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.04,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":1.0,"id":"s1","own":false,"role":"gap","text":"While recent evaluations have started to examine safety across multiple conversational turns, few compare how slight changes in a teen's responses can affect a chatbot's safety in the same scenario.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.05,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.54,"role_probabilities":{"gap":1.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.94,"id":"s2","own":true,"role":"contribution","text":"We conduct a clinician-informed evaluation of chatbot safety in simulated conversations with adolescents aged 13-17, examining how safety failures vary with adolescents' responses and teen-aware system prompting.","hedge":{"p":0.98,"label":"asserted"},"own_p":0.97,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.64,"role_probabilities":{"gap":0.0,"method":0.06,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.94,"interpretation":0.0}},{"i":3,"p":0.99,"id":"s3","own":true,"role":"method","text":"We evaluated 32,555 simulated conversations across 18 chatbot APIs and two system-prompt conditions using 22 safety criteria grounded in previously identified harms.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"method","text":"Conversations spanned 983 variants of 106 seed scenarios covering urgent safety issues, health advice, and identity and relationships.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.03,"quantitative":true,"quantitative_p":0.98,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":5,"p":1.0,"id":"s5","own":true,"role":"result","text":"The overall criterion failure rate was 43.3% without the teen-aware prompt and 24.9% with it.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.14,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":6,"p":0.79,"id":"s6","own":true,"role":"result","text":"The teen-aware prompt reduced failures, but it didn't eliminate them.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.19,"quantitative":false,"quantitative_p":0.13,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.79,"background":0.0,"limitation":0.03,"future_work":0.0,"contribution":0.0,"interpretation":0.18}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"When a teenager pushed back on a chatbot's answer, failures on mental health diagnosis, medication, and substance misuse boundaries rose by 10-12 percentage points without the prompt, for more than 80% of chatbots.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.13,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":8,"p":0.99,"id":"s8","own":true,"role":"interpretation","text":"These findings reveal persistent safety failures in simulated adolescent-chatbot interactions and show that safety depends on how a conversation unfolds.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.88,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.99}}]},"compiled":{"main_claim":{"p":1.0,"text":"These findings reveal persistent safety failures in simulated adolescent-chatbot interactions and show that safety depends on how a conversation unfolds.","location":"abstract s8","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":6959,"cost_usd_reported":0.0},"compiled_at":"2026-11-06","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.08,"states_limitation":0.81,"human_participants":0.16,"controlled_comparison":0.93,"randomized_assignment":0.03,"states_quantitative_result":0.99,"compares_with_prior_results":0.88,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.51,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.51,"simulation_or_computation":0.49}},"contribution_type":{"p":0.72,"value":"empirical study","probabilities":{"review":0.0,"method_or_tool":0.0,"empirical_study":0.72,"simulation_study":0.27,"theoretical_result":0.0,"dataset_or_benchmark":0.01,"position_or_commentary":0.0}},"contribution_statement":{"p":0.99,"text":"We conduct a clinician-informed evaluation of chatbot safety in simulated conversations with adolescents aged 13-17, examining how safety failures vary with adolescents' responses and teen-aware system prompting.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":9,"sentences_in_abstract":9},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448}}