Gradient-Based Attribution

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 77

All topics

IG-Lens: Exact Additive Probability Attribution Across Transformer Layers via Telescoping Integrated Gradients
Jun 29, 2026Duc Anh NguyenGradient-Based Attribution Integrated Gradients
Hanoi University of Science and Technology
Towards Value-Constrained Credit Assignment in Fully Delegated AI Cooperatives
Jun 26, 2026Young Yoon, Jimin Kim, Soyeon ParkGradient-Based Attribution Value Alignment
Hongik University, Seoul, Republic of Korea
GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
Jun 26, 2026Xiaocheng Yang, Abdulrahman Alrabah, Dilek Hakkani-Tür +1Gradient-Based Attribution Multi-Agent LLM Systems
University of Illinois Urbana-Champaign
Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation
Jun 22, 2026Yanze Xu, Mark D. Plumbley, Wenwu WangGradient-Based Attribution Feature Attribution
Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, UK · Department of Informatics, King’s College London, London, WC2R 2LS, UK
Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution
Jun 21, 2026Soyeon Kim, Kyowoon Lee, Jaesik ChoiGradient-Based Attribution Feature Attribution
1KAIST, Korea · 3INEEJI Corp., Korea · 2Ajou University, Korea
Residue-Level Attributions in Protein Language Models Do Not Recover Allergen Epitopes
Jun 20, 2026Jianzhou Yao, Anxiong Song, Katja Baerenfaller +1Gradient-Based Attribution Protein Language Models
Swiss Institute of Allergy and Asthma Research, Davos, Switzerland · ETH Zurich, Zurich, Switzerland · Swiss Institute of Bioinformatics, Lausanne, Switzerland
LIG: Layer-wise Integrated Gradients for Within-Layer Flow Analysis in Transformers
Jun 19, 2026Eight Suzuki, Hideitsu Hino, Noboru MurataGradient-Based Attribution Transformer Interpretability
Waseda University · Fujitsu Limited · The Institute of Statistical Mathematics
Influcoder: Distilling Decoders' Gradient Influence Rankings into an Encoder for Data Attribution
Jun 11, 2026Dimitri Kachler, Damien Sileo, Pascal DenisGradient-Based Attribution Influence Functions
Centre Inria de l’Université de Lille, CRIStAL, Université de Lille
Bergson: An Open Source Library for Data Attribution
Jun 10, 2026Lucia Quirke, Louis Jaburi, David Johnston +6Gradient-Based Attribution LLM Interpretability
EleutherAI · Independent
When Attribution Patching Lies: Diagnosis and a Second-Order Correction
Jun 5, 2026Luyang Zhang, Jialu WangGradient-Based Attribution LLM Interpretability
1Carnegie Mellon University · University of California, Santa Cruz
Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution
Jun 3, 2026Govind Ramesh, Yao Dou, Wei XuGradient-Based Attribution LLM Interpretability
Georgia Institute of Technology
Data Attribution in Large Language Models via Bidirectional Gradient Optimization
Jun 3, 2026Frédéric Berdoz, Luca A. Lanzendörfer, Kaan Bayraktar +1Gradient-Based Attribution LLM Interpretability
ETH Zurich
Attribution via Distributional Paths for Information Revelation
Jun 2, 2026Kieran A. Murphy, Shameen ShresthaGradient-Based Attribution Feature Attribution
New Jersey Institute of Technology
Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detection
May 27, 2026Antonia Šarčević, Nikolina FridGradient-Based Attribution Electroencephalography
University of Zagreb Faculty of Electrical Engineering and Computing, Croatia
Localization then Neutralization: Gradient-guided Token Suppression against Visual Prompt Injection Attack
May 24, 2026Dongpeng Zhang, Ke Ma, Yangbangyan Jiang +4Gradient-Based Attribution VLM Robustness
School of Advanced Interdisciplinary Sciences, UCAS · School of Electronic, Electrical and Communication Engineering, UCAS · School of Computer Science and Technology, UCAS +4
Evaluating the Temporal Detection Capability of Integrated Gradients Applied on Sound Classifier
May 22, 2026Martynas Dumpis, Tuomas VirtanenGradient-Based Attribution Integrated Gradients
Department of Electronic Systems · Vilnius Gediminas Technical University · Vilnius, Lithuania +3
The Neglected Baseline in Model Interpretation
May 21, 2026Yongjin Cui, Xiaohui FanGradient-Based Attribution Integrated Gradients
Zhejiang University
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
Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew
May 18, 2026Joan Serrà, Dipam Goswami, Fabio Morreale +2Gradient-Based Attribution Training Data Attribution
Sony AI · Sony Group Corporation
AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps
May 16, 2026Chia-Ying Hsieh, Hsin-Yuan Fang, Chun-Shu WeiGradient-Based Attribution Saliency Map Evaluation
National Yang Ming Chiao Tung University
Zero-Shot Faithful Textual Explanations via Directional-Derivative Influence on Predictions
May 16, 2026Toshinori Yamauchi, Hiroshi Kera, Kazuhiko KawamotoGradient-Based Attribution Neural Network Interpretability
Chiba University · National Institute of Informatics
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
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
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
How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines
May 12, 2026Junwei Deng, Pingbang Hu, Suliang Jin +4Gradient-Based Attribution Data Selection
University of Illinois Urbana-Champaign · University of Michigan · Princeton University +1
Transformer Interpretability from Perspective of Attention and Gradient
May 12, 2026Yongjin Cui, Xiaohui Fan, Huajun ChenGradient-Based Attribution Transformer Interpretability
Zhejiang University
Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks
May 7, 2026Patrick Elisii, Lucas Beauchemin, Dawer JamshedGradient-Based Attribution Loss of Plasticity
The Vanguard Group, Inc.
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
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
Attribution-Guided Masking for Robust Cross-Domain Sentiment Classification
May 4, 2026Shubham Harkare, Arvind Yogesh Suresh Babu, Yash KulkarniGradient-Based Attribution Sentiment Analysis
University of Michigan

Jun 29, 2026, cs.LGJ/K move · Enter open · S save

IG-Lens: Exact Additive Probability Attribution Across Transformer Layers via Telescoping Integrated Gradients

Duc Anh Nguyen

Hanoi University of Science and Technology

Gradient-Based Attribution Integrated Gradients Transformer Interpretability Decoder-Only Language Models Layer-Wise Relevance Propagation

Open paper AskPDF arXiv

We ask a simple question about decoder-only transformers: between which two layers is the probability of a predicted token actually produced? Existing layer-wise readout tools answer only approximately. The logit lens and its trained variant report a per-layer level of probability but give no additive decomposition; their estimates are biased and non-monotone across depth. Direct Logit Attribution and related residual-stream methods are additive, but only in logit space, the softmax nonlinearity breaks additivity in probability space, precisely the quantity one usually cares about. Layer Conductance integrates gradients per layer, but attributes each to its own baseline and so does not sum to the total change in prediction. We introduce IG-Lens, a telescoping application of Integrated Gradients along a single path through the hidden states from a baseline to the final layer. Crediting each segment to the layer it terminates at yields a layer-wise attribution whose sum is exactly the change in target probability, with the softmax inside the integration path rather than linearized away. Our default estimator credits each integration step its observed change in target probability (a prediction-aware reweighting in the spirit of IDGI) rather than its raw gradient. Because the readout is a one-dimensional probability, this collapses each segment to a telescoping sum of endpoint values, so completeness holds exactly (to floating point) at any step count, removing Riemann discretization error while suppressing steps that show gradient sensitivity without a change in output. We give the telescoping identity and its proof, verify completeness to floating point, and describe a single-pass batched implementation computing the full token-by-layer map without any backward call. Code: https://github.com/anhnda/IGLens.

Momentum

Related topics

Latest papers 77