DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models
This provides a standardized tool for researchers and practitioners to evaluate data attribution methods in LLMs, though it is incremental as it builds on existing methods without introducing new ones.
The authors tackled the lack of systematic evaluation for data attribution methods in large language models by introducing DATE-LM, a unified benchmark that measures attribution quality across tasks like training data selection and toxicity filtering, finding no single method dominates and performance varies with task design.
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, with the motivation that DATE-LM can serve as a foundation for future data attribution research in LLMs.