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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jiao, Cathy, Pan, Yijun, Xiao, Emily, Sheng, Daisy, Jain, Niket, Zhao, Hanzhang, Dasgupta, Ishita, Ma, Jiaqi W., Xiong, Chenyan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911230673813504
author Jiao, Cathy
Pan, Yijun
Xiao, Emily
Sheng, Daisy
Jain, Niket
Zhao, Hanzhang
Dasgupta, Ishita
Ma, Jiaqi W.
Xiong, Chenyan
author_facet Jiao, Cathy
Pan, Yijun
Xiao, Emily
Sheng, Daisy
Jain, Niket
Zhao, Hanzhang
Dasgupta, Ishita
Ma, Jiaqi W.
Xiong, Chenyan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_09424
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models
Jiao, Cathy
Pan, Yijun
Xiao, Emily
Sheng, Daisy
Jain, Niket
Zhao, Hanzhang
Dasgupta, Ishita
Ma, Jiaqi W.
Xiong, Chenyan
Computation and Language
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.
title DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2507.09424