peterbhase

anchor

Code for "High-Precision Model-Agnostic Explanations" paper

evolution-strategies-exploration

Contains implementation of: Tim Salimans Et al. “Evolution Strategies as a Scalable Alternative to Reinforcement Learning”. Arxiv.org. https://arxiv.org/pdf/1703.03864.pdf.

ExplanationRoles

Code for paper "When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data"

ExplanationSearch

Code for paper "Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals"

interpretable-image

Code for "Interpretable Image Recognition with Hierarchical Prototypes"

InterpretableNLP-ACL2020

Code for "Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?"

LAS-NL-Explanations

Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"

mechanistic-interpretability

poetry-generation

Code for "Shall I Compare Thee to a Machine-Written Sonnet? An Algorithmic Approach to Sonnet Generation", available at https://arxiv.org/abs/1811.05067

SLAG-Belief-Updating

Code for paper "Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs"

peterbhase/InterpretableNLP-ACL2020

Code for "Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?"

peterbhase/SLAG-Belief-Updating

Code for paper "Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs"

peterbhase/LAS-NL-Explanations

Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"

peterbhase/ExplanationSearch

Code for paper "Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals"

peterbhase/interpretable-image

Code for "Interpretable Image Recognition with Hierarchical Prototypes"

peterbhase/ExplanationRoles

Code for paper "When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data"

peterbhase/poetry-generation

Code for "Shall I Compare Thee to a Machine-Written Sonnet? An Algorithmic Approach to Sonnet Generation", available at https://arxiv.org/abs/1811.05067

peterbhase/mechanistic-interpretability

peterbhase/anchor

Code for "High-Precision Model-Agnostic Explanations" paper

peterbhase/evolution-strategies-exploration

Contains implementation of: Tim Salimans Et al. “Evolution Strategies as a Scalable Alternative to Reinforcement Learning”. Arxiv.org. https://arxiv.org/pdf/1703.03864.pdf.

peterbhase/peterbhase.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

peterbhase/rome

Rank-One Model Editing for Locating and Editing Factual Knowledge in GPT

peterbhase/tennis_wta

WTA Tennis Rankings, Results, and Stats

peterbhase/transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.