Rank1: Test-Time Compute for Reranking in Information Retrieval
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911097112494080 |
|---|---|
| author | Weller, Orion Ricci, Kathryn Yang, Eugene Yates, Andrew Lawrie, Dawn Van Durme, Benjamin |
| author_facet | Weller, Orion Ricci, Kathryn Yang, Eugene Yates, Andrew Lawrie, Dawn Van Durme, Benjamin |
| contents | We introduce Rank1, the first reranking model trained to take advantage of test-time compute. Rank1 demonstrates the applicability within retrieval of using a reasoning language model (i.e. OpenAI's o1, Deepseek's R1, etc.) for distillation in order to rapidly improve the performance of a smaller model. We gather and open-source a dataset of more than 600,000 examples of R1 reasoning traces from queries and passages in MS MARCO. Models trained on this dataset show: (1) state-of-the-art performance on advanced reasoning and instruction following datasets; (2) work remarkably well out of distribution due to the ability to respond to user-input prompts; and (3) have explainable reasoning chains that can be given to users or RAG-based systems. Further, we demonstrate that quantized versions of these models retain strong performance while using less compute/memory. Overall, Rank1 shows that test-time compute allows for a fundamentally new type of explainable and performant reranker model for search. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18418 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rank1: Test-Time Compute for Reranking in Information Retrieval Weller, Orion Ricci, Kathryn Yang, Eugene Yates, Andrew Lawrie, Dawn Van Durme, Benjamin Information Retrieval Computation and Language Machine Learning We introduce Rank1, the first reranking model trained to take advantage of test-time compute. Rank1 demonstrates the applicability within retrieval of using a reasoning language model (i.e. OpenAI's o1, Deepseek's R1, etc.) for distillation in order to rapidly improve the performance of a smaller model. We gather and open-source a dataset of more than 600,000 examples of R1 reasoning traces from queries and passages in MS MARCO. Models trained on this dataset show: (1) state-of-the-art performance on advanced reasoning and instruction following datasets; (2) work remarkably well out of distribution due to the ability to respond to user-input prompts; and (3) have explainable reasoning chains that can be given to users or RAG-based systems. Further, we demonstrate that quantized versions of these models retain strong performance while using less compute/memory. Overall, Rank1 shows that test-time compute allows for a fundamentally new type of explainable and performant reranker model for search. |
| title | Rank1: Test-Time Compute for Reranking in Information Retrieval |
| topic | Information Retrieval Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2502.18418 |