{"683294":{"#nid":"683294","#data":{"type":"event","title":"Machine Learning Seminar Series Fall 2025 | Asta: Building and Evaluating Scientific AI Assistants","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E AI has tremendous potential for accelerating science---helping researchers access the literature, analyze data, execute experiments, and more. Asta, a project at the Allen Institute for AI, aims to deliver comprehensive scientific assistants that support all aspects of a scientific workflow.\u0026nbsp; Rigorously evaluating such systems is a fundamental challenge, which led us to develop AstaBench, a holistic benchmark suite and leaderboard spanning the scientific discovery process.\u0026nbsp; The work includes evaluations for scientific \u201cdeep research\u201d systems, introducing methods for measuring coverage and precision of both answers and their attributions. Fully realizing AI\u0027s potential for scientists will require breakthroughs in scalable supervision, robust evaluation, and personalized and proactive assistance.\u0026nbsp; To facilitate progress toward these goals, the Asta project provides open-source corpora, tools, and APIs.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBio: \u003C\/strong\u003EDoug Downey is Sr. Director of Semantic Scholar Research at the Allen Institute for AI (Ai2) and a Professor of Computer Science at Northwestern University. His research focuses on Natural Language Processing, with an emphasis on AI systems that support scientific discovery. At Ai2, he helps lead the Asta project, and his publications have received paper awards at ACL, EMNLP, IJCAI, and AKBC.\u003C\/p\u003E\u003Cdiv\u003E\u0026nbsp;\u003C\/div\u003E\u003Cdiv\u003E\u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/95579926750?pwd=pnIsrm72dS3RJXaBMqX4L6HAsbvHV2.1\u0022 target=\u0022_blank\u0022\u003E\u003Cstrong\u003EZoom\u0026nbsp;Access to Seminar\u003C\/strong\u003E\u003C\/a\u003E\u003Cbr\u003E\u003Cstrong\u003EMeeting ID:\u0026nbsp;955 7992 6750\u003C\/strong\u003E\u003Cbr\u003E\u003Cstrong\u003EPasscode:\u003C\/strong\u003E\u0026nbsp;513514\u0026nbsp;\u003C\/div\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003E\u003Cstrong\u003ESeminars Held on Wednesdays 12pm - 1pm\u003C\/strong\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Featuring Douglas Downey - Professor of Computer Science, Northwestern"}],"uid":"27863","created_gmt":"2025-07-25 18:13:50","changed_gmt":"2025-10-15 18:18:52","author":"Christa Ernst","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2025-10-22T12:00:00-04:00","event_time_end":"2025-10-22T13:00:00-04:00","event_time_end_last":"2025-10-22T13:00:00-04:00","gmt_time_start":"2025-10-22 16:00:00","gmt_time_end":"2025-10-22 17:00:00","gmt_time_end_last":"2025-10-22 17:00:00","rrule":null,"timezone":"America\/New_York"},"location":"CODA Building 9th floor Atrium \u0026 Zoom","extras":[],"related_links":[{"url":"https:\/\/www.mccormick.northwestern.edu\/research-faculty\/directory\/profiles\/downey-douglas.html","title":"Speaker Webpage"}],"groups":[{"id":"322011","name":"College of Computing Events"},{"id":"1278","name":"College of Sciences"},{"id":"198081","name":"Georgia Electronic Design Center (GEDC)"},{"id":"545781","name":"Institute for Data Engineering and Science"}],"categories":[],"keywords":[{"id":"9167","name":"machine learning"},{"id":"192863","name":"go-ai"},{"id":"187023","name":"go-data"},{"id":"654","name":"College of Computing"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"177814","name":"Postdoc"},{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}