[Own work] On Measuring Faithfulness or Self-consistency of Natural Language Explanations#Large Language Models#Explainability·youtube.com·Jul 30, 2024[Own work] On Measuring Faithfulness or Self-consistency of Natural Language Explanations
Scaling and evaluating sparse autoencodersView PDF#Large Language Models#Visualization#OpenAI#Paper#PDF#Explainability·arxiv.org·Jun 7, 2024Scaling and evaluating sparse autoencoders
Cultural Bias in Explainable AI Research: A Systematic Analysis | Journal of Artificial Intelligence Research#Explainability#Bias#AI#Paper#PDF·jair.org·Mar 28, 2024Cultural Bias in Explainable AI Research: A Systematic Analysis | Journal of Artificial Intelligence Research
AI agents help explain other AI systems#XAI#Explainability#Interpretability#Agents·news.mit.edu·Jan 8, 2024AI agents help explain other AI systems
Diagnosing AI Explanation Methods with Folk Concepts of Behavior | Journal of Artificial Intelligence Research#XAI#Explainability#Paper#PDF·jair.org·Nov 14, 2023Diagnosing AI Explanation Methods with Folk Concepts of Behavior | Journal of Artificial Intelligence Research
Explainable Goal-driven Agents and Robots - A Comprehensive Review | ACM Computing Surveys#AI#Explainability#Paper#PDF#Review·dl.acm.org·Jun 7, 2023Explainable Goal-driven Agents and Robots - A Comprehensive Review | ACM Computing Surveys
Progress measures for grokking via mechanistic interpretability#Machine Learning#Interpretability#Paper#PDF#Explainability#Deep Learning·arxiv.org·Feb 5, 2023Progress measures for grokking via mechanistic interpretability
Towards Human-Centered Explainable AI: the journey so far#Explainability·thegradient.pub·Dec 13, 2022Towards Human-Centered Explainable AI: the journey so far
Interpretable Machine Learning#Explainability#Machine Learning#Counterfactuals#Book·christophm.github.io·Oct 24, 2022Interpretable Machine Learning
Does this artificial intelligence think like a human?#Machine Learning#Explainability·news.mit.edu·Apr 7, 2022Does this artificial intelligence think like a human?
Software vendors are pushing "explainable A.I." that often isn't#Explainability#AI#Criticism·fortune.com·Mar 28, 2022Software vendors are pushing "explainable A.I." that often isn't
How well do explanation methods for machine-learning models work?#Machine Learning#Explainability·news.mit.edu·Jan 19, 2022How well do explanation methods for machine-learning models work?
"Knowledge Creation and its Risks" - David Deutsch on AGI - Centre for the Future of Intelligence#AGI#Science#Explainability·youtube.com·Oct 15, 2021"Knowledge Creation and its Risks" - David Deutsch on AGI - Centre for the Future of Intelligence
Even experts are too quick to rely on AI explanations, study finds#AI#Explainability#Criticism·venturebeat.com·Aug 26, 2021Even experts are too quick to rely on AI explanations, study finds
Best practices for ML product decisions (ML Tech Talks)#Machine Learning#Prediction#Explainability·youtube.com·Aug 5, 2021Best practices for ML product decisions (ML Tech Talks)