Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2512.16236 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908719957147648 |
|---|---|
| author | Pandit, Tejul Mahendru, Sakshi Raval, Meet Upadhyay, Dhvani |
| author_facet | Pandit, Tejul Mahendru, Sakshi Raval, Meet Upadhyay, Dhvani |
| contents | Reranking is a critical stage in contemporary information retrieval (IR) systems, improving the relevance of the user-presented final results by honing initial candidate sets. This paper is a thorough guide to examine the changing reranker landscape and offer a clear view of the advancements made in reranking methods. We present a comprehensive survey of reranking models employed in IR, particularly within modern Retrieval Augmented Generation (RAG) pipelines, where retrieved documents notably influence output quality.
We embark on a chronological journey through the historical trajectory of reranking techniques, starting with foundational approaches, before exploring the wide range of sophisticated neural network architectures such as cross-encoders, sequence-generation models like T5, and Graph Neural Networks (GNNs) utilized for structural information. Recognizing the computational cost of advancing neural rerankers, we analyze techniques for enhancing efficiency, notably knowledge distillation for creating competitive, lighter alternatives. Furthermore, we map the emerging territory of integrating Large Language Models (LLMs) in reranking, examining novel prompting strategies and fine-tuning tactics. This survey seeks to elucidate the fundamental ideas, relative effectiveness, computational features, and real-world trade-offs of various reranking strategies. The survey provides a structured synthesis of the diverse reranking paradigms, highlighting their underlying principles and comparative strengths and weaknesses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16236 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models Pandit, Tejul Mahendru, Sakshi Raval, Meet Upadhyay, Dhvani Information Retrieval Artificial Intelligence Reranking is a critical stage in contemporary information retrieval (IR) systems, improving the relevance of the user-presented final results by honing initial candidate sets. This paper is a thorough guide to examine the changing reranker landscape and offer a clear view of the advancements made in reranking methods. We present a comprehensive survey of reranking models employed in IR, particularly within modern Retrieval Augmented Generation (RAG) pipelines, where retrieved documents notably influence output quality. We embark on a chronological journey through the historical trajectory of reranking techniques, starting with foundational approaches, before exploring the wide range of sophisticated neural network architectures such as cross-encoders, sequence-generation models like T5, and Graph Neural Networks (GNNs) utilized for structural information. Recognizing the computational cost of advancing neural rerankers, we analyze techniques for enhancing efficiency, notably knowledge distillation for creating competitive, lighter alternatives. Furthermore, we map the emerging territory of integrating Large Language Models (LLMs) in reranking, examining novel prompting strategies and fine-tuning tactics. This survey seeks to elucidate the fundamental ideas, relative effectiveness, computational features, and real-world trade-offs of various reranking strategies. The survey provides a structured synthesis of the diverse reranking paradigms, highlighting their underlying principles and comparative strengths and weaknesses. |
| title | The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2512.16236 |