NLM DIR Seminar Schedule
UPCOMING SEMINARS
-
July 3, 2025 Matthew Diller
Using Ontologies to Make Knowledge Computable -
July 15, 2025 Noam Rotenberg
Cell phenotypes in the biomedical literature: a systematic analysis and the NLM CellLink text mining corpus
RECENT SEMINARS
-
July 3, 2025 Matthew Diller
Using Ontologies to Make Knowledge Computable -
July 1, 2025 Yoshitaka Inoue
Graph-Aware Interpretable Drug Response Prediction and LLM-Driven Multi-Agent Drug-Target Interaction Prediction -
June 10, 2025 Aleksandra Foerster
Interactions at pre-bonding distances and bond formation for open p-shell atoms: a step toward biomolecular interaction modeling using electrostatics -
June 3, 2025 MG Hirsch
Interactions among subclones and immunity controls melanoma progression -
May 29, 2025 Harutyun Sahakyan
In silico evolution of globular protein folds from random sequences
Scheduled Seminars on Oct. 31, 2023
Contact NLMDIRSeminarScheduling@mail.nih.gov with questions about this seminar.
Abstract:
Along with the dramatic growth of interest in artificial intelligence and deep learning is a growth in questions about such algorithms. For example, are they fair? A machine learning algorithm is behind PubMed search's Best Match algorithm. NIST's AI Risk Management Framework points out that fairness needs to be regularly measured and tracked across changes in algorithms. We measured fairness in PubMed search in the areas of article language and journal ranking. We also modified the search algorithm by changing which clicks are used to score articles and adding a dense retrieval feature. We measure the effect on fairness resulting from these changes. We conclude with a discussion of the implementation and implications of a common suggestion for balancing fairness and relevance of search results.