← Authors

Been Kim

26 papers · 2014–2025 · 4 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (11) πŸ—ΊοΈ Taxonomy Completionist (37) 🌈 Renaissance Researcher (6) 🐝 Cross-Pollinator (13) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (4) 🌟 Keyword Trendsetter Combo (5) πŸ‘‘ Triple Crown πŸ† Keyword Champion (3) πŸ”¬ Deep Specialist (12) 🧬 Topic Evolution πŸ—ƒοΈ Keyword Collector (90) πŸ’Ž Century Club (26) ❓ The Questioner πŸš€ Conference Pioneer ⚑ Prolific Year (5) πŸ“ˆ Trend Setter

Conferences

NIPS (15) ICML (6) ICLR (4) AISTATS (1)

Top co-authors

Michael Muelly (3) Julius Adebayo (3) Pieter-jan Kindermans (2) Justin Gilmer (2) Robert Geirhos (2) Asma Ghandeharioun (2) Julie A Shah (2) Rajiv Khanna (2) Martin Wattenberg (2) James Wexler (2)

Keywords

feature importance (4) model interpretability (3) concept-based explanation (3) generative model (2) image classification (2) neural network interpretability (2) out-of-distribution detection (2) feature attribution (2) saliency map (2) saliency method (2) neural network (2) prototype learning (2) knowledge editing (1) sequential decision making (1) feature extraction (1) epistemic uncertainty (1) variational inference (1) uncertainty quantification (1) feature selection (1) explainable ai (1)

Papers

How new data permeates LLM knowledge and how to dilute it ICLR 2025
Position: We Can’t Understand AI Using our Existing Vocabulary ICML 2025
Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty ICML 2025
Don’t trust your eyes: on the (un)reliability of feature visualizations ICML 2024
Gaussian Process Probes (GPP) for Uncertainty-Aware Probing NIPS 2023
Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models NIPS 2023
State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding NIPS 2023
On the Relationship Between Explanation and Prediction: A Causal View ICML 2023
DISSECT: Disentangled Simultaneous Explanations via Concept Traversals ICLR 2022
Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis NIPS 2022
Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation ICLR 2022
Debugging Tests for Model Explanations NIPS 2020
On Completeness-aware Concept-Based Explanations in Deep Neural Networks NIPS 2020
Concept Bottleneck Models ICML 2020
Towards Automatic Concept-based Explanations NIPS 2019
Interpreting Black Box Predictions using Fisher Kernels AISTATS 2019
Visualizing and Measuring the Geometry of BERT NIPS 2019
A Benchmark for Interpretability Methods in Deep Neural Networks NIPS 2019
Learning how to explain neural networks: PatternNet and PatternAttribution ICLR 2018
Sanity Checks for Saliency Maps NIPS 2018
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) ICML 2018
Human-in-the-Loop Interpretability Prior NIPS 2018
To Trust Or Not To Trust A Classifier NIPS 2018
Examples are not enough, learn to criticize! Criticism for Interpretability NIPS 2016
Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction NIPS 2015
The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classification NIPS 2014