paper-with-me

홈 › Papers

A Bayesian Information-Theoretic Approach to Data Attribution

2026-04-04 · Dharmesh Tailor, Nicolò Felicioni, Kamil Ciosek arxiv

Training Data Attribution (TDA) seeks to trace model predictions back to influential training examples, enhancing interpretability and safety. We formulate TDA as a Bayesian information-theoretic problem: subsets are scored by the information loss they induce - the entropy increase at a query when removed. This criterion credits examples for resolving predictive uncertainty rather than label noise. To scale to modern networks, we approximate information loss using a Gaussian Process surrogate built from tangent features. We show this aligns with classical influence scores for single-example attribution while promoting diversity for subsets. For even larger-scale retrieval, we relax to an information-gain objective and add a variance correction for scalable attribution in vector databases. Experiments show competitive performance on counterfactual sensitivity, ground-truth retrieval and coreset selection, showing that our method scales to modern architectures while bridging principled measures with practice.

📄 PDF Abstract BibTeX arXiv:2604.03858

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Attribution Projection Calculus: A Novel Framework for Causal Inference in Bayesian Networks

2025-05-17 · M Ruhul Amin

This paper introduces Attribution Projection Calculus (AP-Calculus), a novel mathematical framework for determining causal relationships in structured Bayesian networks. We investigate a specific network architecture wit…

Causal InferenceFairness

Integrated Marketing Attribution: A Bayesian Framework for Privacy-Safe Granular Measurement Anchored in MMM

2026-06-15 · Meghana R. Bhat, Ankit Umare, Utsav Aggarwal, Richard Vecsler 외 arxiv

Retail marketing measurement increasingly requires granular campaign-level insights without relying on user-level tracking. However, the two dominant approaches, Marketing Mix Modeling (MMM) and Multi-Touch Attribution (…

From Small to Large Language Models: Revisiting the Federalist Papers

2025-02-25 · So Won Jeong, Veronika Ročková

For a long time, the authorship of the Federalist Papers had been a subject of inquiry and debate, not only by linguists and historians but also by statisticians. In what was arguably the first Bayesian case study, Moste…

Authorship AttributionDimensionality ReductionLarge Language Modeltext-classification+2

Information-Theoretic Visual Explanation for Black-Box Classifiers

2020-09-23 · Jihun Yi, Eunji Kim, Siwon Kim, Sungroh Yoon

In this work, we attempt to explain the prediction of any black-box classifier from an information-theoretic perspective. For each input feature, we compare the classifier outputs with and without that feature using two …

A Consistent and Efficient Evaluation Strategy for Attribution Methods

2022-02-01 · Yao Rong, Tobias Leemann, Vadim Borisov, Gjergji Kasneci 외

With a variety of local feature attribution methods being proposed in recent years, follow-up work suggested several evaluation strategies. To assess the attribution quality across different attribution techniques, the m…