DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models

Cathy Jiao, Yijun Pan, Emily Xiao, Daisy Sheng, Niket Jain, Hanzhang Zhao, Ishita Dasgupta, Jiaqi W. Ma, Chenyan Xiong

Keywords: data attribution, evaluation

Abstract: Data attribution methods quantify the influence of training data on model outputs and are becoming increasingly relevant for a wide range of LLM research and applications, including dataset curation, model interpretability, data valuation. However, there remain critical gaps in systematic LLM-centric evaluation of data attribution methods. To this end, we introduce DATE-LM (Data Attribution Evaluation in Language Models), a unified benchmark for evaluating data attribution methods through real-world LLM applications. DATE-LM measures attribution quality through three key tasks — training data selection, toxicity/bias filtering, and factual attribution. Our benchmark is designed for ease of use, enabling researchers to configure and run large-scale evaluations across diverse tasks and LLM architectures. Furthermore, we use DATE-LM to conduct a large-scale evaluation of existing data attribution methods. Our findings show that no single method dominates across all tasks, data attribution methods have trade-offs with simpler baselines, and method performance is sensitive to task-specific evaluation design. Finally, we release a public leaderboard for quick comparison of methods and to facilitate community engagement. We hope DATE-LM serves as a foundation for future data attribution research in LLMs.

Code URL: https://github.com/DataAttributionEval/DATE-LM

Primary Area: Datasets & Benchmarks for applications in language modeling and vision language modeling

Submission Number: 1863