REVIEW 16 cited by
TRAK: Attributing Model Behavior at Scale
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and efficacy. That is, computationally tractable methods can struggle with accurately attributing model predictions in non-convex settings (e.g., in the context of deep neural networks), while methods that are effective in such regimes require training thousands of models, which makes them impractical for large models or datasets. In this work, we introduce TRAK (Tracing with the Randomly-projected After Kernel), a data attribution method that is both effective and computationally tractable for large-scale, differentiable models. In particular, by leveraging only a handful of trained models, TRAK can match the performance of attribution methods that require training thousands of models. We demonstrate the utility of TRAK across various modalities and scales: image classifiers trained on ImageNet, vision-language models (CLIP), and language models (BERT and mT5). We provide code for using TRAK (and reproducing our work) at https://github.com/MadryLab/trak .
Forward citations
Cited by 16 Pith papers
-
A Defense of the Quadratic Model
Local Taylor-expanded quadratic models reproduce a 150M-parameter LLM's validation loss for up to 10% of training late in the run, and LLM pretraining operates within a factor of 2 of a stochastic or deterministic edg...
-
Small edits, large models: How Wikipedia advocacy shapes LLM values
Wikipedia edits by animal welfare advocates measurably influence LLM outputs on animal welfare topics, shown via retrieval and gradient attribution plus fine-tuning experiments.
-
Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation
RISE applies CountSketch to dual lexical and semantic channels derived from output-layer gradient outer products, cutting data attribution storage by up to 112x and enabling retrospective and prospective influence ana...
-
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning
GUDA approximates leave-one-group-out counterfactual models with unlearning and ranks group influence by ELBO differences.
-
BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining
A bilevel optimization method ranks pretraining data by training a small proxy model on weighted samples, yielding modest downstream-task gains without external pretrained models.
-
Understanding Data Influence with Differential Approximation
This paper introduces Diff-In, an influence estimator that accumulates second-order approximations of influence differences across training steps and shows strong accuracy in data cleaning, deletion, and coreset selec...
-
Better Training Data Attribution via Better Inverse Hessian-Vector Products
ASTRA, an EKFAC-preconditioned Neumann series iteration, computes more accurate inverse Hessian-vector products and improves training data attribution scores over EKFAC baselines.
-
The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
A new 8TB openly-licensed text corpus trains 7B LLMs that are competitive with Llama 1/2, showing that performant models need not depend on unlicensed web data.
-
Daunce: Data Attribution through Uncertainty Estimation
DAUNCE computes training-data attribution as the covariance of per-example losses across an ensemble of perturbed fine-tuned models, reporting state-of-the-art LDS scores and the first attribution runs on proprietary LLMs.
-
Laplace Sample Information: Data Informativeness Through a Bayesian Lens
LSI ranks training samples by informativeness using the KL divergence between Laplace-approximated posteriors with and without each sample, and the ordering transfers from a small probe to larger models.
-
KAIROS: Scalable Model-Agnostic Data Valuation
KAIROS derives a closed-form Maximum Mean Discrepancy influence score that approximates leave-one-out data rankings and detects noise, mislabels, and backdoors without retraining.
-
TokenShapley: Token Level Context Attribution with Shapley Value
TokenShapley computes token-level Shapley attributions from context to response by treating context tokens as (prefix, token) data points in a KNN datastore.
-
Rescaled Influence Functions: Accurate Data Attribution in High Dimension
Rescaled influence functions, which account for the change in the Hessian when a sample is removed, dramatically improve leave-T-out effect estimates compared to standard influence functions in high-dimensional logist...
-
Efficient Data Selection at Scale via Influence Distillation
Influence Distillation selects LLM fine-tuning data by approximating each sample's gradient influence on a target task via landmarks and JVP embeddings, matching or beating RDS+ accuracy at roughly one third the selec...
-
Scaling laws for activation steering with Llama 2 models and refusal mechanisms
Activation steering with contrastive vectors becomes less effective as Llama 2 models scale from 7B to 70B parameters, with peak effect at roughly 40% of the model's layers.
-
Attributing Data for Sharpness-Aware Minimization
SAM-HIF and SAM-GIF are proposed as data attribution scores for SAM-trained models, but SAM-GIF is TracIn with SAM gradients and SAM-HIF's derivation contains a load-bearing error.
Discussion (0). Continue with ORCID to comment.