CoRECT: A Framework for Evaluating Embedding Compression Techniques at Scale
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917205440987136 |
|---|---|
| author | Caspari, L. Dinzinger, M. Dastidar, K. Ghosh Fellicious, C. Mitrović, J. Granitzer, M. |
| author_facet | Caspari, L. Dinzinger, M. Dastidar, K. Ghosh Fellicious, C. Mitrović, J. Granitzer, M. |
| contents | Dense retrieval systems have proven to be effective across various benchmarks, but require substantial memory to store large search indices. Recent advances in embedding compression show that index sizes can be greatly reduced with minimal loss in ranking quality. However, existing studies often overlook the role of corpus complexity -- a critical factor, as recent work shows that both corpus size and document length strongly affect dense retrieval performance. In this paper, we introduce CoRECT (Controlled Retrieval Evaluation of Compression Techniques), a framework for large-scale evaluation of embedding compression methods, supported by a newly curated dataset collection. To demonstrate its utility, we benchmark eight representative types of compression methods. Notably, we show that non-learned compression achieves substantial index size reduction, even on up to 100M passages, with statistically insignificant performance loss. However, selecting the optimal compression method remains challenging, as performance varies across models. Such variability highlights the necessity of CoRECT to enable consistent comparison and informed selection of compression methods. All code, data, and results are available on GitHub and HuggingFace. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19340 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoRECT: A Framework for Evaluating Embedding Compression Techniques at Scale Caspari, L. Dinzinger, M. Dastidar, K. Ghosh Fellicious, C. Mitrović, J. Granitzer, M. Information Retrieval Dense retrieval systems have proven to be effective across various benchmarks, but require substantial memory to store large search indices. Recent advances in embedding compression show that index sizes can be greatly reduced with minimal loss in ranking quality. However, existing studies often overlook the role of corpus complexity -- a critical factor, as recent work shows that both corpus size and document length strongly affect dense retrieval performance. In this paper, we introduce CoRECT (Controlled Retrieval Evaluation of Compression Techniques), a framework for large-scale evaluation of embedding compression methods, supported by a newly curated dataset collection. To demonstrate its utility, we benchmark eight representative types of compression methods. Notably, we show that non-learned compression achieves substantial index size reduction, even on up to 100M passages, with statistically insignificant performance loss. However, selecting the optimal compression method remains challenging, as performance varies across models. Such variability highlights the necessity of CoRECT to enable consistent comparison and informed selection of compression methods. All code, data, and results are available on GitHub and HuggingFace. |
| title | CoRECT: A Framework for Evaluating Embedding Compression Techniques at Scale |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2510.19340 |