BK

Been Kim

0000-0001-9938-2915

cs.LGstat.MLcs.AIcs.CVcs.CLArtificial Intelligencecs.HCq-bio.NCartificial intelligencecs.NE

On Valency

published · living versions

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

with Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler +2

1 version

W_bg4e778xv1 · current

A Heart Means Recursion: Exploring Visual Meaning and Communication in VLMs

W_ybgbmu8qv1

Preprints & journals

68 papers in the corpus · 2013–2026

XYEval: Agents say yes to bad advice

Zhengxuan Wu, Yuxuan Li, Oyvind Tafjord et al.

0 citations

2609.23939v12026arXiv

Visual prompt engineering for video models

Robert Geirhos, Yuxuan Li, Thaddaus Wiedemer et al.

0 citations

2607.25537v12026arXiv

Representational Similarity and Model Behavior in Multi-Agent Interaction

Yujin Potter, Seun Eisape, Shiyang Lai et al.

0 citations

2606.07818v12026arXiv

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits

Neha Kalibhat, Zi Wang, Prasoon Bajpai et al.

0 citations

2602.00092v12026Twenty-Ninth Annual Conference on Artificial Intelligence and Statistics (AISTATS 2026)

Neologism Learning for Controllability and Self-Verbalization

John Hewitt, Oyvind Tafjord, Robert Geirhos et al.

1 citation

2510.08506v12025arXiv

Video models are zero-shot learners and reasoners

Thaddaus Wiedemer, Yuxuan Li, Paul Vicol et al.

2 citations

2509.20328v22025arXiv

How many classes do we need to see for novel class discovery?

Akanksha Sarkar, Been Kim, Jennifer J. Sun

0 citations

2509.15585v12025arXiv

Escaping Plato's Cave: JAM for Aligning Independently Trained Vision and Language Models

Lauren Hyoseo Yoon, Yisong Yue, Been Kim

0 citations

2507.01201v72025arXiv

Because we have LLMs, we Can and Should Pursue Agentic Interpretability

Been Kim, John Hewitt, Neel Nanda et al.

1 citation

2506.12152v12025arXiv

How new data permeates LLM knowledge and how to dilute it

Chen Sun, Renat Aksitov, Andrey Zhmoginov et al.

1 citation

2504.09522v12025arXiv

QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?

Belinda Z. Li, Been Kim, Zi Wang

0 citations

2503.22674v2202539th Conference on Neural Information Processing Systems (NeurIPS 2025) Track on Datasets and Benchmarks

Bridging the human-AI knowledge gap through concept discovery and transfer in AlphaZero.

Schut, Lisa, Tomašev, Nenad, McGrath, Thomas et al.

15 citations

401383462025Proceedings of the National Academy of Sciences of the United States of America. 2025;122(13):e2406675122

We Can't Understand AI Using our Existing Vocabulary

John Hewitt, Robert Geirhos, Been Kim

1 citation

2502.07586v12025arXiv

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

Meera Hahn, Wenjun Zeng, Nithish Kannen et al.

0 citations

2412.06771v32024International Conference on Machine Learning, 2025

Future views on neuroscience and AI.

Witten, Ilana, Yamins, Daniel L K, Clopath, Claudia et al.

1 citation

394238002024Cell. 2024;187(21):5809-5813

Impossibility theorems for feature attribution.

Bilodeau, Blair, Jaques, Natasha, Koh, Pang Wei et al.

108 citations

381810572024Proceedings of the National Academy of Sciences of the United States of America. 2024;121(2):e2304406120

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

Lisa Schut, Nenad Tomasev, Tom McGrath et al.

9 citations

2310.16410v12023arXiv

Getting aligned on representational alignment

Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller et al.

35 citations

2310.13018v32023arXiv

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

Devleena Das, Sonia Chernova, Been Kim

5 citations

2309.12482v22023arXiv

Human Intelligence and the Connectome are Driven by Structural Brain Network Control

Anderson, E. D., Varshney, L. R., Hemmatian, B. et al.

1 citation

10.1101/2023.08.02.551642v12023bioRxiv

Don't trust your eyes: on the (un)reliability of feature visualizations

Robert Geirhos, Roland S. Zimmermann, Blair Bilodeau et al.

5 citations

2306.04719v62023arXiv

Socially intelligent machines that learn from humans and help humans learn.

Gweon, Hyowon, Fan, Judith, Kim, Been

18 citations

372711772023Philosophical transactions. Series A, Mathematical, physical, and engineering sciences. 2023;381(2251):20220048

Gaussian Process Probes (GPP) for Uncertainty-Aware Probing

Zi Wang, Alexander Ku, Jason Baldridge et al.

5 citations

2305.18213v2202337th Conference on Neural Information Processing Systems (NeurIPS 2023)

Model evaluation for extreme risks

Toby Shevlane, Sebastian Farquhar, Ben Garfinkel et al.

62 citations

2305.15324v22023arXiv

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

Peter Hase, Mohit Bansal, Been Kim et al.

33 citations

2301.04213v22023arXiv

On the Relationship Between Explanation and Prediction: A Causal View

Amir-Hossein Karimi, Krikamol Muandet, Simon Kornblith et al.

4 citations

2212.06925v42022arXiv

Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation

Julius Adebayo, Michael Muelly, Hal Abelson et al.

28 citations

2212.04629v12022ICLR 2022 conference paper

Acquisition of chess knowledge in AlphaZero.

McGrath, Thomas, Kapishnikov, Andrei, Tomašev, Nenad et al.

106 citations

363750612022Proceedings of the National Academy of Sciences of the United States of America. 2022;119(47):e2206625119

Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis

Shayegan Omidshafiei, Andrei Kapishnikov, Yannick Assogba et al.

1 citation

2206.09046v32022arXiv

Advanced Methods for Connectome-Based Predictive Modeling of Human Intelligence: A Novel Approach Based on Individual Differences in Cortical Topography

Evan D. Anderson, Ramsey Wilcox, Anuj Nayak et al.

1 citation

2203.00707v22022arXiv

Human-Centered Concept Explanations for Neural Networks

Chih-Kuan Yeh, Been Kim, Pradeep Ravikumar

12 citations

2202.12451v12022arXiv

Subgoal-Based Explanations for Unreliable Intelligent Decision Support Systems

Devleena Das, Been Kim, Sonia Chernova

13 citations

2201.04204v32022arXiv

Analyzing a Caching Model

Leon Sixt, Evan Zheran Liu, Marie Pellat et al.

0 citations

2112.06989v22021arXiv

Best of both worlds: local and global explanations with human-understandable concepts

Jessica Schrouff, Sebastien Baur, Shaobo Hou et al.

14 citations

2106.08641v22021arXiv

DISSECT: Disentangled Simultaneous Explanations via Concept Traversals

Asma Ghandeharioun, Been Kim, Chun-Liang Li et al.

13 citations

2105.15164v42021arXiv

Debugging Tests for Model Explanations

Julius Adebayo, Michael Muelly, Ilaria Liccardi et al.

73 citations

2011.05429v12020arXiv

Concept Bottleneck Models

Pang Wei Koh, Thao Nguyen, Yew Siang Tang et al.

328 citations

2007.04612v32020arXiv

On Completeness-aware Concept-Based Explanations in Deep Neural Networks

Chih-Kuan Yeh, Been Kim, Sercan O. Arik et al.

134 citations

1910.07969v62019arXiv

Benchmarking Attribution Methods with Relative Feature Importance

Mengjiao Yang, Been Kim

84 citations

1907.09701v22019arXiv

Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems

Shalmali Joshi, Oluwasanmi Koyejo, Warut Vijitbenjaronk et al.

94 citations

1907.09615v12019arXiv

Explaining Classifiers with Causal Concept Effect (CaCE)

Yash Goyal, Amir Feder, Uri Shalit et al.

93 citations

1907.07165v22019arXiv

Visualizing and Measuring the Geometry of BERT

Andy Coenen, Emily Reif, Ann Yuan et al.

296 citations

1906.02715v22019arXiv

Neural Networks Trained on Natural Scenes Exhibit Gestalt Closure

Been Kim, Emily Reif, Martin Wattenberg et al.

43 citations

1903.01069v42019arXiv

Human-Centered Tools for Coping with Imperfect Algorithms during Medical Decision-Making

Carrie J. Cai, Emily Reif, Narayan Hegde et al.

404 citations

1902.02960v12019arXiv

Towards Automatic Concept-based Explanations

Amirata Ghorbani, James Wexler, James Zou et al.

378 citations

1902.03129v32019arXiv

An Evaluation of the Human-Interpretability of Explanation

Isaac Lage, Emily Chen, Jeffrey He et al.

125 citations

1902.00006v22019arXiv

Human Evaluation of Models Built for Interpretability.

Lage, Isaac, Chen, Emily, He, Jeffrey et al.

113 citations

336239332022Proceedings of the ... AAAI Conference on Human Computation and Crowdsourcing. 2019;7(1):59-67

Human-in-the-Loop Interpretability Prior.

Lage, Isaac, Ross, Andrew Slavin, Kim, Been et al.

79 citations

336233542022Advances in neural information processing systems. 2018;31

Interpreting Black Box Predictions using Fisher Kernels

Rajiv Khanna, Been Kim, Joydeep Ghosh et al.

56 citations

1810.10118v12018arXiv

Sanity Checks for Saliency Maps

Julius Adebayo, Justin Gilmer, Michael Muelly et al.

1,294 citations

1810.03292v32018arXiv

Career total: 100 works. 68 are in this corpus.Showing the 50 most recent.

Profile built from the corpus for this byline.

100

works

14.1K

citations

42

h-index

Corpus papers per year

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.