Feature Attribution

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, down 7% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 147

All topics

The Attribution Contract: Feature Attribution for Generative Language Models
May 21, 2026Giang NguyenFeature Attribution LLM Interpretability
Guide Labs
Proxy-Based Approximation of Shapley and Banzhaf Interactions
May 21, 2026Santo M. A. R. Thies, Hubert Baniecki, R. Teal Witter +3Feature Attribution Feature Interaction Modeling
LMU Munich · MCML · DFKI +4
The Neglected Baseline in Model Interpretation
May 21, 2026Yongjin Cui, Xiaohui FanGradient-Based Attribution Integrated Gradients
Zhejiang University
Efficient Higher-order Subgraph Attribution via Message Passing
May 21, 2026Ping Xiong, Thomas Schnake, Grégoire Montavon +2Feature Attribution Layer-Wise Relevance Propagation
Technische Universität Berlin (TU Berlin) · BIFOLD – Berlin Institute for the Foundations of Learning and Data · Department of Artificial Intelligence, Korea University, Seoul 136-713, Korea +2
Towards Explainability of SLMs by investigating Token Level Activation
May 21, 2026Sayantani Ghosh, Rajashik Datta, Amit Kumar Das +1Transformer Interpretability Feature Attribution
Information Technology, A.K. Choudhury School of Information Technology, Kolkata, West Bengal, India. · Computer Science & Engineering(Artificial Intelligence), Institute of Engineering & Management, Kolkata, 700091, West Bengal, India. · Computer Science & Engineering, Institute of Engineering & Management, Kolkata, 700091, West Bengal, India. +1
A Unified Framework for Uncertainty-Aware Explainable Artificial Intelligence: A Case Study in Power Quality Disturbance Classification
May 20, 2026Yinsong Chen, Samson S. Yu, Zhong Li +1Bayesian Neural Networks Feature Attribution
School of Engineering, Deakin University, Melbourne, 3216, VIC, Australia · Faculty of Mathematics and Computer Science, FernUniversität in Hagen, 58084, Germany · Department of Computing Technologies, Swinburne University of Technology, Hawthorn, 3122, VIC, Australia
Multi-Resolution Attribution from Adaptive Routing State
May 19, 2026Joss ArmstrongFeature Attribution
Ericsson, Athlone, Ireland
B-cos GNNs: Faithful Explanations through Dynamic Linearity
May 19, 2026Joschka Groß, Mohammad Shaique Solanki, Verena WolfFeature Attribution Graph Neural Networks
Saarland Informatics Campus, Saarland University · DFKI
Spectral Integrated Gradients for Coarse-to-Fine Feature Attribution
May 19, 2026Soyeon Kim, Seongwoo Lim, Kyowoon Lee +1Gradient-Based Attribution Integrated Gradients
Korea Advanced Institute of Science and Technology Seongnam, Gyeonggi-do, Republic of Korea · INEEJI Corp. Seongnam, Gyeonggi-do, Republic of Korea
Generalized Functional ANOVA in Closed-Form: A Unified View of Additive Explanations
May 18, 2026Baptiste Ferrere, Nicolas Bousquet, Fabrice Gamboa +1Feature Attribution Interpretable ML
EDF R&D, SINCLAIR Lab · Université de Toulouse · Sorbonne Université +2
Unsupervised Domain Shift Detection with Interpretable Subspace Attribution
May 15, 2026Sebastian Springer, Alessandro LaioFeature Attribution Distribution Shift
SISSA
Attribute-Grounded Selective Reasoning for Artwork Emotion Understanding with Multimodal Large Language Models
May 15, 2026Cheng Zhang, Yuer Liu, Zhiyu Zhou +2Feature Attribution Multimodal Large Language Models
Department of Computer Science and Technology, Jilin University, Changchun, China · Department of Computer Science, National Taiwan University, Taipei, Taiwan
AGOP-IxG: A Gradient Covariance Filter for Local Feature Attribution on Tabular Data, with a Controlled Benchmark
May 15, 2026Raj Kiran Gupta KatakamGradient-Based Attribution Feature Attribution
Credit Karma
From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks
May 14, 2026Thodoris Lymperopoulos, Denia KanellopoulouFeature Attribution Perturbation-Based Feature Attribution
NCSR Demokritos Athens, Greece
RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attribution
May 14, 2026Lanxin Xiang, Liang Shi, Youhui Ye +3Feature Attribution Shapley Value Attribution
Department of Statistics Virginia Tech · Department of Statistics Virginia Tech Transportation Institute · Department of Computer Science Virginia Tech
How to Evaluate and Refine your CAM
May 14, 2026Luca Domeniconi, Alessandra Stramiglio, Michele Lombardi +1Feature Attribution Explainability Evaluation
University of Bologna, Bologna, Italy
AGOP as Explanation: From Feature Learning to Per-Sample Attribution in Image Classifiers
May 12, 2026Raj Kiran Gupta KatakamGradient-Based Attribution Feature Attribution
Credit Karma, San Francisco, CA, USA
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
May 12, 2026Shixing Yu, Promit Ghosal, Kyra GanFeature Attribution LLM Auditing
Electrical and Computer Engineering · Cornell Tech · Department of Statistics +2
Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions
May 12, 2026Gideon Popoola, John SheppardFeature Attribution Counterfactual Explanations
Gianforte School of Computing Montana State University Bozeman, MT, USA, 59715
A New Technique for AI Explainability using Feature Association Map
May 12, 2026Sayantani Ghosh, Amit Kumar Das, Amlan ChakrabartiFeature Attribution Explainable Artificial Intelligence
1DBS Bank. · Institute of Engineering & Management. · 1,2,3University of Calcutta.
FAME: Feature Activation Map Explanation on Image Classification and Face Recognition
May 12, 2026Xinyi Zhang, Manuel GüntherGradient-Based Attribution Feature Attribution
Department of Informatics, University of Zurich
Attribution-based Explanations for Markov Decision Processes
May 10, 2026Paul Kobialka, Andrea Pferscher, Francesco Leofante +3Feature Attribution Markov Decision Processes
University of Oslo, Norway · Imperial College London, United Kingdom · RWTH Aachen University, Germany
Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks
May 8, 2026Kyle Higgins, Ivan Laponogov, Dennis Veselkov +1Cancer Genomics Feature Attribution
1Division of Cancer, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK. · Department of Computing, Imperial College London, U.K. · Department of Environmental Health Sciences, Yale University, New Haven, CT, USA.
FRInGe: Distribution-Space Integrated Gradients with Fisher--Rao Geometry
May 7, 2026Gabriele Martino, Sebastian TschiatschekGradient-Based Attribution Integrated Gradients
Faculty of Computer Science / Doctoral School Computer Science University of Vienna Vienna, Austria · Faculty of Computer Science / ds:UniVie University of Vienna Vienna, Austria
Can Attribution Predict Risk? From Multi-View Attribution to Planning Risk Signals in End-to-End Autonomous Driving
May 7, 2026Le Yang, Ruoyu Chen, Haijun Liu +3Feature Attribution End-to-End Autonomous Driving
1Sun Yat-sen University · University of Chinese Academy of Sciences · 3Nanyang Technological University
Playing the network backward: A Game Theoretic Attribution Framework
May 7, 2026Jakob Paul Zimmermann, Jim Berend, Georg Loho +2Gradient-Based Attribution Transformer Interpretability
Fraunhofer Heinrich-Hertz-Institute, Berlin, Germany. · Technische Universität Berlin, Berlin, Germany. · Freie Universität Berlin, Berlin, Germany. +2
QuadraSHAP: Stable and Scalable Shapley Values for Product Games via Gauss-Legendre Quadrature
May 7, 2026Majid Mohammadi, Grigory Reznikov, Pavel Sinitcyn +2Cooperative Game Theory Feature Attribution
AI Technology for Life, Information and Computing Sciences, Utrecht University, The Netherlands · Biomolecular Mass Spectrometry and Proteomics, Pharmaceutical Sciences, Utrecht University, The Netherlands · Rational Intelligence Lab, CISPA Helmholtz Center for Information Security, Germany +1
GRALIS: A Unified Canonical Framework for Linear Attribution Methods via Riesz Representation
May 6, 2026Raimondo FanaleFeature Attribution Shapley Value Attribution
Universitas Mercatorum, Rome, Italy.
Seeing What Shouldn't Be There: Counterfactual GANs for Medical Image Attribution
May 6, 2026Shakeeb MurtazaFeature Attribution Counterfactual Explanations
COMSATS University Islamabad
Feature importance analysis for patient management decisions
May 6, 2026Michal Valko, Milos HauskrechtFeature Attribution Healthcare
Department of Computer Science, University of Pittsburgh, Pittsburgh, PA

May 21, 2026, cs.LGJ/K move · Enter open · S save

The Attribution Contract: Feature Attribution for Generative Language Models

Giang Nguyen

Guide Labs

Feature Attribution LLM Interpretability

Open paper AskPDF arXiv

Feature attribution methods promise to identify which input features matter for a model output. In generative language models, however, it is often unclear what should count as a feature in the first place. In autoregressive language models, earlier generated tokens are both outputs of the model and inputs to later predictions. In diffusion language models, generation proceeds through iterative denoising or unmasking rather than fixed left-to-right prediction, so local explanation may target a state of diffusion rather than a next token. We argue that this ambiguity is not merely an implementation detail, but a conceptual limitation of carrying classifier-era feature attribution directly into generative language modeling. We introduce the Attribution Contract, a specification for feature-attribution claims that names what output is being explained, which features are eligible to receive attribution, what generative process is assumed, what is held fixed, and what model score is being attributed. The contract clarifies why the same attribution method can answer different questions depending on how it is instantiated. We argue that many disagreements about feature attribution in generative language models are not disagreements about attribution algorithms, but about unstated explanatory contracts. Using autoregressive and diffusion language models as case studies, we show when attribution to earlier generated tokens, intermediate states, or denoising stages is informative, when it is misleading, and why feature-attribution methods in generative language models should be evaluated as method-contract pairs.

Momentum

Related topics

Latest papers 147