Training Data Attribution

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 250% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 60

All topics

Attributing HOW, Not Just WHICH: Counterfactual Response Trajectories for Diffusion Models
Oct 8, 2026Haoqian Zhang, Ziyuan Yang, Zerui Shao +1Training Data Attribution Diffusion Models
Sichuan University
Which Rollout Taught It That? BehaviorTrace and the Limits of Training-Data Attribution in Online RL
Oct 7, 2026Amit NautiyalGradient-Based Attribution Training Data Attribution
Independent Researcher
TICDA: Tabular In-Context Data Attribution
Oct 6, 2026Yacine Benihaddadene, Milan Bhan, Eliot Dugelay +4Tabular Foundation Models Tabular ICL
Ekimetrics · ETH Zurich
Generation Provenance Before Behavior Attribution: Auditing Synthetic Speech Research Objects
Oct 1, 2026Sidi Chang, Peiying ZhuData Provenance Training Data Attribution
Blossom AI Labs Blossom AI Tokyo, Japan
TrueMuse: A Benchmark for Data Attribution in Text-to-Music Models
Sep 30, 2026Jiawei Yu, Jian LiuText-to-Music Generation Audio Diffusion Models
School of Computing University of Georgia
Source Identification Is Not Fitness Testing: Measuring the Limits of Synthetic-Data Attribution
Sep 30, 2026Joss ArmstrongModel Collapse Training Data Attribution
Ericsson, Athlone, Ireland
Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution
Sep 30, 2026Shixuan Liu, Joan Serrà, Kin Wai Cheuk +6Gradient-Based Attribution Training Data Attribution
University of Illinois at Urbana-Champaign · Sony AI · University of Texas at Austin +1
dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM Scale
Sep 30, 2026Shixuan Liu, Tongli Zhou, Junwei Deng +2Gradient-Based Attribution Training Data Attribution
University of Illinois at Urbana-Champaign · Google
The Unequal Influence of Bad Advice: Using Training Data Attribution to Modulate Emergent Misalignment
Sep 29, 2026Gonçalo Paulo, Louis Jaburi, Nora Belrose +2LLM Alignment LLM Fine-Tuning
EleutherAI
Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection
Sep 29, 2026Jaeseung Heo, J Rosser, Dongwoo KimGradient Compression Influence Functions
POSTECH · University of Oxford
Scalable Attribution and Control of Model Behavior During Training
Sep 27, 2026Sleem AbdelghafarGradient-Based Attribution Causal Interventions in Language Models
Rice University
Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss
Sep 27, 2026Yi Ren, Wenlong Deng, Guanzhe Hong +2Continual Learning for LLMs Loss of Plasticity
OATML · University of Oxford · UBC +1
Traceprop: Training Data Attribution in a Single Pass
Sep 26, 2026Amit NautiyalGradient-Based Attribution Training Data Attribution
Independent Researcher
Can Data Attribution Filter Out Subliminal Learning? Not Reliably
Sep 17, 2026Moritz Weckbecker, Sweta Jena, Jonas Müller +5Gradient-Based Attribution Training Data Curation
Department of Artificial Intelligence, Fraunhofer Heinrich Hertz Institute · International Institute of Information Technology Hyderabad · Department of Electrical Engineering and Computer Science, Technische Universität Berlin +4
Form Over Content In Gradient-Based Data Attribution Methods
Sep 17, 2026Sunwoo Kim, Seokwon Jung, Sohyung Kim +2Gradient-Based Attribution Instruction-Tuning Data Selection
KAIST
Data Attribution at Scale via Influence Matrix Estimation
Sep 14, 2026Yuxi Chen, Hamza Golubovic, Han Tong +2Influence Functions Training Data Attribution
Carnegie Mellon University 1Department of Statistics & Data Science · Columbia University 2Department of Statistics · Columbia University 3Electrical Engineering Department +2
Attributing Cohen's d: Training Data Attribution for Disease-Related Effects in Normative Age Biomarkers
Sep 7, 2026Jakob Snel, Marc-Andre SchulzBrain Age Prediction Influence Functions
Hertie Institute for AI in Brain Health, University of Tübingen, Tübingen, Germany · Tübingen AI Center, University of Tübingen, Tübingen, Germany · Department of Psychiatry and Neurosciences, Charité – Universitätsmedizin Berlin, Berlin, Germany +1
From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution
Sep 2, 2026Yuzhang Luo, Chenpeng Wang, Jianhui Chen +1Training Data Attribution Influence Functions
State Key Laboratory of Multimedia Information Processing, Peking University · YiXin-AILab, YIXIN, Beijing, China · Beijing Academy of Artificial Intelligence, Beijing, China +1
Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models
Aug 30, 2026Rania Briq, Ohad Fried, Michael Kamp +1Flow Matching Flow-Based Generative Modeling
Forschungszentrum Jülich · Technical University Dortmund · Reichman University +4
Learned, Then Lost: A Measured Single-Example Counterfactual in Pre-training
Aug 19, 2026Zachary Speck, Asa ShepardLanguage Model Pretraining Memorization in Language Models
Arizona State University · Williams College
Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining
Aug 13, 2026Yuto Nishida, Hirokazu Kiyomaru, Yusuke Oda +6Language Model Pretraining Gradient-Based Attribution
Nara Institute of Science and Technology · NII LLMC · Waseda University +3
Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints
Aug 3, 2026Zirui Huang, Yunlong Mao, Wei Tong +3Language Model Fingerprinting Training Data Attribution
State Key Laboratory of Novel Software Technology, Nanjing University Nanjing, Jiangsu, China
How Context Attribution Handles What the Model Already Knows
Jul 26, 2026Quoc-Huy Trinh, Lin Zhu, Sebastian SzyllerLLM Evaluation LLM Interpretability
Aalto University
Directional Influence Function: Estimating Training Data Influence in Constrained Learning
Jul 25, 2026Xin Wang, R. Tyrrell Rockafellar, Xuegang +1Influence Functions Training Data Attribution
Jeff · Department of Civil and Environmental Engineering University of Washington Seattle, WA, USA · Department of Mathematics University of Washington Seattle, WA, USA
Fisher Rank Inflation: A Spectral Signature of Memorization under Label Noise
Jul 14, 2026Satwik Bathula, Anand A. JoshiNeural Network Memorization Noisy-Label Learning
Department of Electrical and Computer Engineering, University of Southern California
From Neural Network Decisions to Training Cases: An Exact Account via Case-Based Decision Theory
Jul 13, 2026Manli Yan, Yuebin Lin, Yaowen Yu +1Algorithmic Auditing Neural Network Interpretability
Huazhong University of Science and Technology Wuhan, China
Influence Diagnostics in High-dimensional M-estimation: Precise Asymptotics
Jul 10, 2026Hugo CuiInfluence Functions Training Data Attribution
Université Paris-Saclay, CNRS, Laboratoire de mathématiques d’Orsay, 91405, Orsay, France
Validation-Induced Shapley Shifts: How Validation Structure Distorts Data Valuation
Jul 4, 2026Yinan Shen, Ziao Yang, Hongfu LiuShapley Value Attribution Data Valuation
Adobe Waltham, MA 02451, USA · Department of Computer Science Brandeis University Waltham, MA 02453-2728, USA
WARP: Weight-Space Analysis for Recovering Training Data Portfolios
Jul 2, 2026Tzu-Heng Huang, Aditya Goyal, John Cooper +1Weight-Space Analysis Training Data Attribution
University of Wisconsin-Madison
What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music
Jul 1, 2026Luyang Zhang, Xirui Jiang, Junwei Deng +3Mechanism Design Data Valuation
Carnegie Mellon University · University of Michigan, Ann Arbor · University of Illinois Urbana-Champaign

Oct 8, 2026, cs.CVJ/K move · Enter open · S save

Attributing HOW, Not Just WHICH: Counterfactual Response Trajectories for Diffusion Models

Haoqian Zhang, Ziyuan Yang, Zerui Shao, Yi Zhang

Sichuan University

Training Data Attribution Diffusion Models Concept-Based Explanations

Open paper AskPDF arXiv

Diffusion models have achieved remarkable success in image generation, yet tracing their outputs to individual training examples remains challenging. Existing attribution methods often compress factor-specific effects into scalar responses, making distinct internal changes indistinguishable. This is particularly limiting for diffusion models, where semantic factors emerge through evolving representation dynamics during denoising. We therefore reformulate diffusion data attribution as attributing factor-induced internal response trajectories. In this paper, we propose a novel Concept Attribution method through Dynamic Trajectories(CADT). We argue that attribution should therefore ask not only \emph{which} examples matter, but also \emph{how} their influence unfolds during generation. Specifically, we construct matched counterfactual pairs at identical noisy states to isolate factor-specific representation displacements, and model their directional and magnitude evolution across denoising as dynamic attribution signatures. For each training example and generated query, CADT extracts stage-wise feature vectors and integrates them along the denoising process to form a trajectory descriptor. Applying the same construction across the training set yields a bank of factor-specific trajectory descriptors. The covariance statistics of this bank are then used to construct . CADT uses this covariance-aware positive-semidefinite kernel to calibrate the query and training representations, and compares the calibrated query trajectory with each training trajectory to produce the final training-sample attribution scores. Experiments on multiple public datasets show consistent improvements over existing diffusion attribution baselines across hierarchical, compositional, and style attribution.

Momentum

Related topics

Latest papers 60