Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908750550401024 |
|---|---|
| author | George, Sherine |
| author_facet | George, Sherine |
| contents | Retrieval-Augmented Generation (RAG) couples a retriever with a large language model (LLM) to ground generated responses in external evidence. While this framework enhances factuality and domain adaptability, it faces a key bottleneck: balancing retrieval recall with limited LLM context. Retrieving too few passages risks missing critical context, while retrieving too many overwhelms the prompt window, diluting relevance and increasing cost.
We propose a two-stage retrieval pipeline that integrates LLM-driven query expansion to improve candidate recall and FlashRank, a fast marginal-utility reranker that dynamically selects an optimal subset of evidence under a token budget. FlashRank models document utility as a weighted combination of relevance, novelty, brevity, and cross-encoder evidence. Together, these modules form a generalizable solution that increases answer accuracy, faithfulness, and computational efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03258 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion George, Sherine Information Retrieval Retrieval-Augmented Generation (RAG) couples a retriever with a large language model (LLM) to ground generated responses in external evidence. While this framework enhances factuality and domain adaptability, it faces a key bottleneck: balancing retrieval recall with limited LLM context. Retrieving too few passages risks missing critical context, while retrieving too many overwhelms the prompt window, diluting relevance and increasing cost. We propose a two-stage retrieval pipeline that integrates LLM-driven query expansion to improve candidate recall and FlashRank, a fast marginal-utility reranker that dynamically selects an optimal subset of evidence under a token budget. FlashRank models document utility as a weighted combination of relevance, novelty, brevity, and cross-encoder evidence. Together, these modules form a generalizable solution that increases answer accuracy, faithfulness, and computational efficiency. |
| title | Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2601.03258 |