Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.01833 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909562111524864 |
|---|---|
| author | Shashidhar, Sumuk Fourrier, Clémentine Lozovskia, Alina Wolf, Thomas Tur, Gokhan Hakkani-Tür, Dilek |
| author_facet | Shashidhar, Sumuk Fourrier, Clémentine Lozovskia, Alina Wolf, Thomas Tur, Gokhan Hakkani-Tür, Dilek |
| contents | Evaluating large language models (LLMs) effectively remains a critical bottleneck, as traditional static benchmarks suffer from saturation and contamination, while human evaluations are costly and slow. This hinders timely or domain-specific assessment, crucial for real-world applications. We introduce YourBench, a novel, open-source framework that addresses these limitations by enabling dynamic, automated generation of reliable, up-to-date, and domain-tailored benchmarks cheaply and without manual annotation, directly from user-provided documents. We demonstrate its efficacy by replicating 7 diverse MMLU subsets using minimal source text, achieving this for under 15 USD in total inference costs while perfectly preserving the relative model performance rankings (Spearman Rho = 1) observed on the original benchmark. To ensure that YourBench generates data grounded in provided input instead of relying on posterior parametric knowledge in models, we also introduce Tempora-0325, a novel dataset of over 7K diverse documents, published exclusively after March 2025. Our comprehensive analysis spans 26 SoTA models from 7 major families across varying scales (3-671B parameters) to validate the quality of generated evaluations through rigorous algorithmic checks (e.g., citation grounding) and human assessments. We release the YourBench library, the Tempora-0325 dataset, 150k+ question answer pairs based on Tempora and all evaluation and inference traces to facilitate reproducible research and empower the community to generate bespoke benchmarks on demand, fostering more relevant and trustworthy LLM evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01833 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | YourBench: Easy Custom Evaluation Sets for Everyone Shashidhar, Sumuk Fourrier, Clémentine Lozovskia, Alina Wolf, Thomas Tur, Gokhan Hakkani-Tür, Dilek Computation and Language Artificial Intelligence I.2.1 Evaluating large language models (LLMs) effectively remains a critical bottleneck, as traditional static benchmarks suffer from saturation and contamination, while human evaluations are costly and slow. This hinders timely or domain-specific assessment, crucial for real-world applications. We introduce YourBench, a novel, open-source framework that addresses these limitations by enabling dynamic, automated generation of reliable, up-to-date, and domain-tailored benchmarks cheaply and without manual annotation, directly from user-provided documents. We demonstrate its efficacy by replicating 7 diverse MMLU subsets using minimal source text, achieving this for under 15 USD in total inference costs while perfectly preserving the relative model performance rankings (Spearman Rho = 1) observed on the original benchmark. To ensure that YourBench generates data grounded in provided input instead of relying on posterior parametric knowledge in models, we also introduce Tempora-0325, a novel dataset of over 7K diverse documents, published exclusively after March 2025. Our comprehensive analysis spans 26 SoTA models from 7 major families across varying scales (3-671B parameters) to validate the quality of generated evaluations through rigorous algorithmic checks (e.g., citation grounding) and human assessments. We release the YourBench library, the Tempora-0325 dataset, 150k+ question answer pairs based on Tempora and all evaluation and inference traces to facilitate reproducible research and empower the community to generate bespoke benchmarks on demand, fostering more relevant and trustworthy LLM evaluation. |
| title | YourBench: Easy Custom Evaluation Sets for Everyone |
| topic | Computation and Language Artificial Intelligence I.2.1 |
| url | https://arxiv.org/abs/2504.01833 |