Sparks of Artificial General Intelligence: Early experiments with GPT-4

Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, +11

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningIntelligent SystemsLarge Language Model +14

Capabilities of GPT-4 on Medical Challenge Problems

Harsha Nori, Nicholas King, Scott Mayer McKinney, +2

arXiv (Cornell University)

Llm Fine-tuningEngineeringMedical TechnologyLarge Language ModelCorpus Linguistics +19

Interpreting Interpretability: Understanding Data Scientists' Use of Interpretability Tools for Machine Learning

Harmanpreet Kaur, Harsha Nori, Samuel Jenkins, +3

EngineeringMachine LearningMachine Learning ToolData VisualizationInterpretability Tools +17

InterpretML: A Unified Framework for Machine Learning Interpretability

Harsha Nori, Samuel Jenkins, Paul Koch, +1

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningComputer AnalysisMachine Learning Tool +19

Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine

Harsha Nori, Yin Tat Lee, Sheng Zhang, +15

arXiv (Cornell University)

Artificial IntelligenceLlm Fine-tuningEngineeringMachine LearningSystem Medicine +19

Supporting Human-AI Collaboration in Auditing LLMs with LLMs

Charvi Rastogi, Marco Túlio Ribeiro, Nicholas S. P. King, +2

Intelligible and Explainable Machine Learning

Rich Caruana, Scott Lundberg, Marco Túlio Ribeiro, +2

Artificial IntelligenceInterpretable Machine LearningEngineeringMachine LearningData Science +12

Comparing Population Means Under Local Differential Privacy: With Significance and Power

Bolin Ding, Harsha Nori, Paul Li, +1

Proceedings of the AAAI Conference on Artificial Intelligence

Privacy ProtectionEngineeringInformation SecurityPopulation MeansVerification +18

Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values

Zijie J. Wang, Alex Kale, Harsha Nori, +6

Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

GAM Changer: Editing Generalized Additive Models with Interactive Visualization

Zijie J. Wang, Alex Kale, Harsha Nori, +6

arXiv (Cornell University)

EngineeringMachine LearningMachine Learning ToolInteractive Data ExplorationComputer-aided Design +16