Data Attribution in Large Language Models via Bidirectional Gradient Optimization
- URL: http://arxiv.org/abs/2606.04928v1
- Date: Wed, 03 Jun 2026 14:21:53 GMT
- Title: Data Attribution in Large Language Models via Bidirectional Gradient Optimization
- Abstract summary: Large Language Models (LLMs) are increasingly deployed across diverse applications.<n>understanding which training data most influenced a model's output remains a fundamental open problem.<n>We address this challenge by expanding upon the inverse formulation: How would training data be affected if the model had seen the generated output during training?<n>Our method perturbs the base model using bidirectional gradient optimization (gradient ascent and descent) on a generated text sample and measures the resulting change in loss across training samples.
- Score: 35.61634772862795
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models (LLMs) are increasingly deployed across diverse applications, raising critical questions for governance, accountability, and data provenance. Understanding which training data most influenced a model's output remains a fundamental open problem. We address this challenge through training data attribution (TDA) for auto-regressive LLMs by expanding upon the inverse formulation: How would training data be affected if the model had seen the generated output during training? Our method perturbs the base model using bidirectional gradient optimization (gradient ascent and descent) on a generated text sample and measures the resulting change in loss across training samples. Our framework supports attribution at arbitrary data granularity, enabling both factual and stylistic attribution. We evaluate our method against baselines on pretrained models with known datasets, and show that it outperforms previous work on influence metrics, thereby enhancing model interpretability, an essential requirement for accountable AI systems.
Related papers
- STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations [46.963298896594814]
Training Data Attribution seeks to trace a model's predictions back to its training data.<n>Most approaches approximate this effect in the parameter space using gradients.<n>We model the functional effect of training data in the activation space.
arXiv Detail & Related papers (2026-06-03T17:59:36Z) - Nonparametric Data Attribution for Diffusion Models [57.820618036556084]
Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs.<n>We propose a nonparametric attribution method that operates entirely on data, measuring influence via patch-level similarity between generated and training images.
arXiv Detail & Related papers (2025-10-16T03:37:16Z) - What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? [83.83230167222852]
We find that a model's generalization behavior can be effectively characterized by a training metric we call pre-memorization train accuracy.
By connecting a model's learning behavior to its generalization, pre-memorization train accuracy can guide targeted improvements to training strategies.
arXiv Detail & Related papers (2024-11-12T09:52:40Z) - Scalable Influence and Fact Tracing for Large Language Model Pretraining [14.598556308631018]
Training data attribution (TDA) methods aim to attribute model outputs back to specific training examples.<n>We refine existing gradient-based methods to work effectively at scale.<n>We release our prompt set and model outputs, along with a web-based visualization tool to explore influential examples.
arXiv Detail & Related papers (2024-10-22T20:39:21Z) - Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review [50.78587571704713]
Learn-Focus-Review (LFR) is a dynamic training approach that adapts to the model's learning progress.<n>LFR tracks the model's learning performance across data blocks (sequences of tokens) and prioritizes revisiting challenging regions of the dataset.<n>Compared to baseline models trained on the full datasets, LFR consistently achieved lower perplexity and higher accuracy.
arXiv Detail & Related papers (2024-09-10T00:59:18Z) - Data Shapley in One Training Run [88.59484417202454]
Data Shapley provides a principled framework for attributing data's contribution within machine learning contexts.<n>Existing approaches require re-training models on different data subsets, which is computationally intensive.<n>This paper introduces In-Run Data Shapley, which addresses these limitations by offering scalable data attribution for a target model of interest.
arXiv Detail & Related papers (2024-06-16T17:09:24Z) - Distilled Datamodel with Reverse Gradient Matching [74.75248610868685]
We introduce an efficient framework for assessing data impact, comprising offline training and online evaluation stages.
Our proposed method achieves comparable model behavior evaluation while significantly speeding up the process compared to the direct retraining method.
arXiv Detail & Related papers (2024-04-22T09:16:14Z) - Unlearning Traces the Influential Training Data of Language Models [31.33791825286853]
This paper presents UnTrac: unlearning traces the influence of a training dataset on the model's performance.
We propose a more scalable approach, UnTrac-Inv, which unlearns a test dataset and evaluates the unlearned model on training datasets.
arXiv Detail & Related papers (2024-01-26T23:17:31Z) - How Training Data Impacts Performance in Learning-based Control [67.7875109298865]
This paper derives an analytical relationship between the density of the training data and the control performance.
We formulate a quality measure for the data set, which we refer to as $rho$-gap.
We show how the $rho$-gap can be applied to a feedback linearizing control law.
arXiv Detail & Related papers (2020-05-25T12:13:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.