been kim

Beenkim's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 15 papers 6 days ago

Towards A Rigorous Science of Interpretable Machine Learning

Paper • 1702.08608 • Published Feb 28, 2017

Learning how to explain neural networks: PatternNet and PatternAttribution

Paper • 1705.05598 • Published May 16, 2017

SmoothGrad: removing noise by adding noise

Paper • 1706.03825 • Published Jun 12, 2017

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

Paper • 1711.11279 • Published Nov 30, 2017

A Benchmark for Interpretability Methods in Deep Neural Networks

Paper • 1806.10758 • Published Jun 28, 2018

Towards Automatic Concept-based Explanations

Paper • 1902.03129 • Published Feb 7, 2019

Benchmarking Attribution Methods with Relative Feature Importance

Paper • 1907.09701 • Published Jul 23, 2019

Model evaluation for extreme risks

Paper • 2305.15324 • Published May 24, 2023

On the Relationship Between Explanation and Prediction: A Causal View

Paper • 2212.06925 • Published Dec 13, 2022

Impossibility Theorems for Feature Attribution

Paper • 2212.11870 • Published Dec 22, 2022

Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models

Paper • 2301.04213 • Published Jan 10, 2023

Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty

Paper • 2412.06771 • Published Dec 9, 2024

State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding

Paper • 2309.12482 • Published Sep 21, 2023

We Can't Understand AI Using our Existing Vocabulary

Paper • 2502.07586 • Published Feb 11 • 10

How new data permeates LLM knowledge and how to dilute it

Paper • 2504.09522 • Published 9 days ago • 7