AI agents trained through competitive debate can allow polynomial-time human judges to oversee PSPACE-level questions, with MNIST experiments boosting sparse classifier accuracy from 59% to 89% using only 6 pixels.
Interpretable and Pedagogical Examples
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Teachers intentionally pick the most informative examples to show their students. However, if the teacher and student are neural networks, the examples that the teacher network learns to give, although effective at teaching the student, are typically uninterpretable. We show that training the student and teacher iteratively, rather than jointly, can produce interpretable teaching strategies. We evaluate interpretability by (1) measuring the similarity of the teacher's emergent strategies to intuitive strategies in each domain and (2) conducting human experiments to evaluate how effective the teacher's strategies are at teaching humans. We show that the teacher network learns to select or generate interpretable, pedagogical examples to teach rule-based, probabilistic, boolean, and hierarchical concepts.
representative citing papers
Advanced AI systems are unexplainable in full and produce explanations that humans cannot comprehend.
citing papers explorer
-
AI safety via debate
AI agents trained through competitive debate can allow polynomial-time human judges to oversee PSPACE-level questions, with MNIST experiments boosting sparse classifier accuracy from 59% to 89% using only 6 pixels.
-
Unexplainability and Incomprehensibility of Artificial Intelligence
Advanced AI systems are unexplainable in full and produce explanations that humans cannot comprehend.