Efficient Listwise Reranking with Compressed Document Representations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918474120429568 |
|---|---|
| author | Déjean, Hervé Clinchant, Stéphane |
| author_facet | Déjean, Hervé Clinchant, Stéphane |
| contents | Reranking, the process of refining the output from a first-stage retriever, is often considered computationally expensive, especially when using Large Language Models (LLMs). A common approach to mitigate this cost involves utilizing smaller LLMs or controlling input length. Inspired by recent advances in document compression for retrieval-augmented generation (RAG), we introduce RRK, an efficient and effective listwise reranker compressing documents into multi-token fixed-size embedding representations. Our simple training via distillation shows that this combination of rich compressed representations and listwise reranking yields a highly efficient and effective system. In particular, our 8B-parameter model runs 3x-18x faster than smaller rerankers (0.6-4B parameters) while matching or outperforming them in effectiveness. The efficiency gains are even more striking on long-document benchmarks, where RRK widens its advantage further. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26483 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Efficient Listwise Reranking with Compressed Document Representations Déjean, Hervé Clinchant, Stéphane Information Retrieval Reranking, the process of refining the output from a first-stage retriever, is often considered computationally expensive, especially when using Large Language Models (LLMs). A common approach to mitigate this cost involves utilizing smaller LLMs or controlling input length. Inspired by recent advances in document compression for retrieval-augmented generation (RAG), we introduce RRK, an efficient and effective listwise reranker compressing documents into multi-token fixed-size embedding representations. Our simple training via distillation shows that this combination of rich compressed representations and listwise reranking yields a highly efficient and effective system. In particular, our 8B-parameter model runs 3x-18x faster than smaller rerankers (0.6-4B parameters) while matching or outperforming them in effectiveness. The efficiency gains are even more striking on long-document benchmarks, where RRK widens its advantage further. |
| title | Efficient Listwise Reranking with Compressed Document Representations |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2604.26483 |