Picture for Lisa Schut

Lisa Schut

Michael Pokorny

Do Multilingual LLMs Think In English?

Add code
Feb 21, 2025
Viaarxiv icon

Humanity's Last Exam

Add code
Jan 24, 2025
Viaarxiv icon

Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs

Add code
Jun 22, 2024
Viaarxiv icon

Explaining Explainability: Understanding Concept Activation Vectors

Add code
Apr 04, 2024
Viaarxiv icon

Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero

Add code
Oct 25, 2023
Viaarxiv icon

Diversifying AI: Towards Creative Chess with AlphaZero

Add code
Aug 29, 2023
Figure 1 for Diversifying AI: Towards Creative Chess with AlphaZero
Figure 2 for Diversifying AI: Towards Creative Chess with AlphaZero
Figure 3 for Diversifying AI: Towards Creative Chess with AlphaZero
Figure 4 for Diversifying AI: Towards Creative Chess with AlphaZero
Viaarxiv icon

DeDUCE: Generating Counterfactual Explanations Efficiently

Add code
Nov 29, 2021
Figure 1 for DeDUCE: Generating Counterfactual Explanations Efficiently
Figure 2 for DeDUCE: Generating Counterfactual Explanations Efficiently
Figure 3 for DeDUCE: Generating Counterfactual Explanations Efficiently
Figure 4 for DeDUCE: Generating Counterfactual Explanations Efficiently
Viaarxiv icon

Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties

Add code
Mar 16, 2021
Figure 1 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Figure 2 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Figure 3 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Figure 4 for Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Viaarxiv icon

A Bayesian Perspective on Training Speed and Model Selection

Add code
Oct 27, 2020
Figure 1 for A Bayesian Perspective on Training Speed and Model Selection
Figure 2 for A Bayesian Perspective on Training Speed and Model Selection
Figure 3 for A Bayesian Perspective on Training Speed and Model Selection
Figure 4 for A Bayesian Perspective on Training Speed and Model Selection
Viaarxiv icon

Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search

Add code
Jun 08, 2020
Figure 1 for Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search
Figure 2 for Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search
Figure 3 for Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search
Figure 4 for Revisiting the Train Loss: an Efficient Performance Estimator for Neural Architecture Search
Viaarxiv icon