{"article":{"annotation":{"article_id":"duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps","available_at":"2026-10-16T10:37:03.483222Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"c9a5cabdd0ca744d840e978e1907d3a745a0e8c9856f1a974cb4d9364bf3c64e","input_sha256":"be667451b8c6a0647b47bf8206ff671764ac24b94347a3597ed95001f8f2b9ea","limitations":["Rule-derived subjects are candidates, not verified editorial labels or calibrated model probabilities.","Coverage is distinct from event location. Unknown country/city/coordinates remain absent; no automatic geocoding.","Article geometries keep their stated precision and methodology; reproducing them is not independent coordinate verification."],"method":"controlled-rules-v1","places":[{"admin1":null,"city":null,"coordinate_note":null,"coordinate_reference_system":"OGC:CRS84","coordinate_source":null,"country":"US","evidence":[{"field":"country","language":"en","note":"Explicit preserved editorial country/region; no city or national centroid inferred","source_urls":["https://law.duke.edu/news/how-well-do-chatbots-and-humans-agree-legal-reasonableness"]}],"geometry":null,"id":"iso3166-1:US","kind":"country-or-area","labels":{"ar":"الولايات المتحدة الأمريكية","en":"United States of America","es":"Estados Unidos de América","fr":"États-Unis d’Amérique"},"match_status":"candidate","precision":"regional","role":"coverage","uncertainty_m":null}],"rules_sha256":"fb5ad3c27c91cb840f7a0a05f7f64a5cb26ad0374409ff9457f277c7092e22b4","schema_version":1,"subjects":[{"concept_id":"medtop:13000000","confidence":null,"confidence_method":null,"evidence":[{"field":"category+topics","language":"en","note":"Preserved editorial category/topic; broad candidate only","source_urls":["https://law.duke.edu/news/how-well-do-chatbots-and-humans-agree-legal-reasonableness"]}],"method":"controlled-rules-v1","rule_id":"technology-broad","status":"candidate"}],"taxonomy_revision":"1f2db31d811fca07e99b16d402c10e2cc2965c9df1c7b41d9be348b40a24e7fb","taxonomy_version":"IPTC Media Topics 2026-Q2"},"api_url":"https://newsverum.com/api/v1/articles/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps?lang=en","category":"technology","content":{"key_points":[],"paragraphs":["Duke Law summarized the research in a 15 October report. The study compared answers from 500 people and 26 AI models—including systems from ChatGPT, Claude, Gemini, Llama, Grok and DeepSeek—across 25 legally relevant scenarios asking what would be “reasonable.” The paper had appeared as an arXiv preprint and was accepted to the AAAI/ACM Conference on AI, Ethics, and Society.","Researchers reported that model answers broadly tracked human judgments but clustered more narrowly than people’s responses. In some scenarios, models gave government and corporations more leeway than individuals; their answers also tended to align more with older, white, male and college-educated respondents. The team says the findings need further testing with more diverse participants and a broader range of chatbots."],"sections":[]},"corrections":[],"country":"US","data":{"blocks":[{"description":{"ar":"تقييمات لما يعد «معقولاً» عبر 25 سيناريو قانونياً.","de":"Bewertung dessen, was in 25 rechtlichen Szenarien „angemessen“ war.","en":"Assessments of what was “reasonable” across 25 legal scenarios.","es":"Evaluaciones de lo que era «razonable» en 25 escenarios legales.","fr":"Évaluations de ce qui était « raisonnable » dans 25 scénarios juridiques.","pt":"Avaliações do que seria «razoável» em 25 cenários jurídicos.","tr":"25 hukuki senaryoda “makul” görülen yanıtları değerlendirme."},"id":"study-record","items":[{"date":"2026-10-15","description":{"ar":"500 مشاركاً و26 نموذجاً للذكاء الاصطناعي و25 سيناريو.","de":"500 Teilnehmende, 26 KI-Modelle und 25 Szenarien.","en":"500 participants, 26 AI models and 25 scenarios.","es":"500 participantes, 26 modelos de IA y 25 escenarios.","fr":"500 participants, 26 modèles d’IA et 25 scénarios.","pt":"500 participantes, 26 modelos de IA e 25 cenários.","tr":"500 katılımcı, 26 AI modeli ve 25 senaryo."},"label":{"ar":"مقارنة إجابات البشر والنماذج","de":"Vergleich menschlicher Antworten und Modelle","en":"Human and model comparison","es":"Comparación entre respuestas humanas y modelos","fr":"Comparaison entre réponses humaines et modèles","pt":"Comparação de respostas humanas e modelos","tr":"İnsan ve model karşılaştırması"},"status":"occurred"}],"methodology":{"ar":"المنهج والنتائج وفق ملخص ديوك وبحث arXiv. وتقتصر النتائج على عينة الدراسة وسيناريوهاتها ولا تثبت أداءً موثقاً في أحكام المحاكم.","de":"Methoden und Ergebnisse laut Duke und arXiv-Arbeit. Die Ergebnisse sind auf Stichprobe und Szenarien begrenzt und belegen keine validierte Leistung in Gerichtsverfahren.","en":"Methods and findings as reported by Duke and the arXiv paper. Results are limited to the study sample and scenarios; they do not establish validated courtroom decision performance.","es":"Métodos y hallazgos según Duke y el artículo de arXiv. Los resultados se limitan a la muestra y escenarios del estudio; no validan el desempeño en tribunales.","fr":"Méthode et résultats selon Duke et l’article arXiv. Les résultats se limitent à l’échantillon et aux scénarios étudiés; ils ne valident pas une performance judiciaire en conditions réelles.","pt":"Métodos e resultados conforme Duke e o artigo do arXiv. Os resultados se limitam à amostra e aos cenários do estudo e não comprovam desempenho validado em tribunais.","tr":"Duke’un haber özeti ve arXiv makalesindeki yöntem ve bulgular. Sonuçlar çalışmadaki katılımcı örneklemi ve senaryolarla sınırlıdır; mahkemelerde doğrulanmış karar performansı göstermez."},"sourceUrls":["https://law.duke.edu/news/how-well-do-chatbots-and-humans-agree-legal-reasonableness"],"title":{"ar":"دراسة المعقولية القانونية","de":"Studie zu rechtlicher Angemessenheit","en":"Legal-reasonableness study","es":"Estudio de razonabilidad jurídica","fr":"Étude sur le caractère raisonnable en droit","pt":"Estudo de razoabilidade jurídica","tr":"Hukuki makullük çalışması"},"type":"events","updatedAt":"2026-10-16T10:20:41+00:00"}],"version":1},"data_downloads":[{"formats":{"csv":"https://newsverum.com/api/v1/articles/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps/data/study-record?lang=en&format=csv","json":"https://newsverum.com/api/v1/articles/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps/data/study-record?lang=en&format=json"},"id":"study-record"}],"data_types":["events"],"editorial_illustration":{"alt":"Conceptual illustration of technology, processors and connected information.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"en","scope":"topic","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"event_id":"event-1800ea43-e9fe-550b-a7d6-b4e9ffeec2ba","event_period":"2026-10-15","event_period_basis":"event-or-reference-period","id":"duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps","image":null,"importance":0.6,"language":"en","modified_at":"2026-10-16T10:36:24+00:00","publication_basis":"publication-record","published_at":"2026-10-16T10:36:24+00:00","reading_minutes":1,"region":"world","relations":[],"section_illustration":{"alt":"Conceptual illustration of technology, processors and connected information.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"en","scope":"section","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"slug":"duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps","sources":[{"checkedAt":"2026-10-16","name":"Duke University School of Law","publishedAt":"2026-10-15","url":"https://law.duke.edu/news/how-well-do-chatbots-and-humans-agree-legal-reasonableness"}],"summary":"Researchers compared 500 people’s responses with 26 language models across 25 legal scenarios; model answers were more uniform and sometimes more favorable to institutions.","text":"Researchers compared 500 people’s responses with 26 language models across 25 legal scenarios; model answers were more uniform and sometimes more favorable to institutions.\n\nDuke Law summarized the research in a 15 October report. The study compared answers from 500 people and 26 AI models—including systems from ChatGPT, Claude, Gemini, Llama, Grok and DeepSeek—across 25 legally relevant scenarios asking what would be “reasonable.” The paper had appeared as an arXiv preprint and was accepted to the AAAI/ACM Conference on AI, Ethics, and Society.\n\nResearchers reported that model answers broadly tracked human judgments but clustered more narrowly than people’s responses. In some scenarios, models gave government and corporations more leeway than individuals; their answers also tended to align more with older, white, male and college-educated respondents. The team says the findings need further testing with more diverse participants and a broader range of chatbots.","title":"Duke study finds chatbots mirror some human legal judgments but diverge","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps"},{"api_url":"https://newsverum.com/api/v1/articles/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps?lang=en","language":"en","url":"https://newsverum.com/en/news/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps"},{"api_url":"https://newsverum.com/api/v1/articles/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps"},{"api_url":"https://newsverum.com/api/v1/articles/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps"},{"api_url":"https://newsverum.com/api/v1/articles/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps?lang=es","language":"es","url":"https://newsverum.com/es/news/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps"},{"api_url":"https://newsverum.com/api/v1/articles/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps?lang=de","language":"de","url":"https://newsverum.com/de/news/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps"},{"api_url":"https://newsverum.com/api/v1/articles/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps"}],"url":"https://newsverum.com/en/news/duke-study-finds-chatbots-align-with-human-legal-reasoning-with-gaps"},"version":"1"}