Interpretability

CVPR 2025arXiv:2411.16198

#2

Interpreting Object-level Foundation Models via Visual Precision Search

Ruoyu Chen, Siyuan Liang, Jingzhi Li et al.

18

CVPR 2025arXiv:2503.20483

#3

Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability

Yingdong Shi, Changming Li, Yifan Wang et al.

diffusion modelssocial bias mitigationmechanistic interpretabilitybias features+2

15

ICLR 2025arXiv:2502.09994

#4

Decision Information Meets Large Language Models: The Future of Explainable Operations Research

Yansen Zhang, Qingcan Kang, Wing Yin YU et al.

13

ICLR 2025arXiv:2502.20914

#5

Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?

Maxime Méloux, Silviu Maniu, François Portet et al.

12

ICLR 2025arXiv:2402.02933

#6

Intrinsic User-Centric Interpretability through Global Mixture of Experts

Vinitra Swamy, Syrielle Montariol, Julian Blackwell et al.

interpretable neural networksconditional computationmixture of expertssparse feature activation+4

10

ICLR 2024arXiv:2310.00164

#7

PRIME: Prioritizing Interpretability in Failure Mode Extraction

Keivan Rezaei, Mehrdad Saberi, Mazda Moayeri et al.

failure mode extractionimage classification modelsinterpretable conceptshuman-understandable descriptions+2

9

ICML 2024arXiv:2307.07084

#8

Learning Robust Rationales for Model Explainability: A Guidance-Based Approach

Shuaibo Hu, Kui Yu

Shedding Light on Time Series Classification using Interpretability Gated Networks

Yunshi Wen, Tengfei Ma, Ronny Luss et al.

Probabilistic Constrained Reinforcement Learning with Formal Interpretability

YANRAN WANG, QIUCHEN QIAN, David Boyle

reinforcement learningprobabilistic inferencepolicy optimizationinterpretable ai+4

ICML 2024arXiv:2310.07918

#11

Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning

Jannik Deuschel, Caleb Ellington, Yingtao Luo et al.

interpretable policy learningmedical decision modelingadaptive imitation learningcontextualized policy recovery+4

ICML 2025arXiv:2506.08216

#12

What makes an Ensemble (Un) Interpretable?

Shahaf Bassan, Guy Amir, Meirav Zehavi et al.

AAAI 2025arXiv:2401.10938

#13

Even-if Explanations: Formal Foundations, Priorities and Complexity

Gianvincenzo Alfano, Sergio Greco, Domenico Mandaglio et al.

ICML 2024arXiv:2405.17425

#14

From Neurons to Neutrons: A Case Study in Interpretability

Ouail Kitouni, Niklas Nolte, Víctor Samuel Pérez-Díaz et al.

mechanistic interpretabilityneural network interpretabilitylow-dimensional representationsnuclear physics concepts+2

4

ICLR 2025arXiv:2410.21331

#15

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness

Qi Zhang, Yifei Wang, Jingyi Cui et al.

feature monosemanticitymodel robustnessinterpretability tradeoffpolysemantic neurons+4

4

ICLR 2024arXiv:2402.03348

#16

Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition

Sangyu Han, Yearim Kim, Nojun Kwak

4

ICLR 2025arXiv:2410.21815

#17

A General Theoretical Framework for Learning Smallest Interpretable Models

Sebastian Ordyniak, Giacomo Paesani, Mateusz Banany et al.

Neural Reasoning for Sure Through Constructing Explainable Models

Tiansi Dong, Mateja Jamnik, Pietro Liò

Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers

Shaobo Wang, Hongxuan Tang, Mingyang Wang et al.

3

ICML 2025arXiv:2501.17077

#20

Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning

Anna Soligo, Pietro Ferraro, David Boyle

NEURIPS 2025arXiv:2511.20273

#21

Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits

Areeb Ahmad, Abhinav Joshi, Ashutosh Modi

transformer interpretabilitymechanistic interpretabilitysingular vector analysiscircuit analysis+4

NEURIPS 2025arXiv:2510.21998

#22

From Black-box to Causal-box: Towards Building More Interpretable Models

Inwoo Hwang, Yushu Pan, Elias Bareinboim

CVPR 2025arXiv:2511.07974

#23

Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition

ZHANG LINTONG, Kang Yin, Seong-Whan Lee

ICML 2025arXiv:2407.13594

#24

Validating Mechanistic Interpretations: An Axiomatic Approach

Nils Palumbo, Ravi Mangal, Zifan Wang et al.

1

ICML 2025arXiv:2502.06775

#25

Enhancing Performance of Explainable AI Models with Constrained Concept Refinement

Geyu Liang, Senne Michielssen, Salar Fattahi

mechanistic interpretabilityvision language modelsactivation patchingsparse autoencoders+3

#26

Mechanistic Interpretability Meets Vision Language Models: Insights and Limitations

Yiming Liu, Yuhui Zhang, Serena Yeung

ICLR 2025

ICLR 2024arXiv:2202.09914

#27

Towards Global-level Mechanistic Interpretability: A Perspective of Modular Circuits of Large Language Models

Yinhan He, Wendy Zheng, Yushun Dong et al.

SOInter: A Novel Deep Energy-Based Interpretation Method for Explaining Structured Output Models

S. Fatemeh Seyyedsalehi, Mahdieh Baghshah, Hamid Rabiee

attention mechanismcategorical reasoningnumerical reasoningin-context learning+4

#29

Adaptive Transformer Programs: Bridging the Gap Between Performance and Interpretability in Transformers

Quoc-Vinh Lai-Dang, Taemin Kang, Seungah Son

ICLR 2025

#30

Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision

Weibo Gao, Qi Liu, Hao Wang et al.

AAAI 2024