Hierarchical Re-ranker Retriever (HRR)

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Singh, Ashish, Mohapatra, Priti
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910857691136000
author Singh, Ashish
Mohapatra, Priti
author_facet Singh, Ashish
Mohapatra, Priti
contents Retrieving the right level of context for a given query is a perennial challenge in information retrieval - too large a chunk dilutes semantic specificity, while chunks that are too small lack broader context. This paper introduces the Hierarchical Re-ranker Retriever (HRR), a framework designed to achieve both fine-grained and high-level context retrieval for large language model (LLM) applications. In HRR, documents are split into sentence-level and intermediate-level (512 tokens) chunks to maximize vector-search quality for both short and broad queries. We then employ a reranker that operates on these 512-token chunks, ensuring an optimal balance neither too coarse nor too fine for robust relevance scoring. Finally, top-ranked intermediate chunks are mapped to parent chunks (2048 tokens) to provide an LLM with sufficiently large context.
format Preprint
id arxiv_https___arxiv_org_abs_2503_02401
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hierarchical Re-ranker Retriever (HRR)
Singh, Ashish
Mohapatra, Priti
Information Retrieval
Computation and Language
Retrieving the right level of context for a given query is a perennial challenge in information retrieval - too large a chunk dilutes semantic specificity, while chunks that are too small lack broader context. This paper introduces the Hierarchical Re-ranker Retriever (HRR), a framework designed to achieve both fine-grained and high-level context retrieval for large language model (LLM) applications. In HRR, documents are split into sentence-level and intermediate-level (512 tokens) chunks to maximize vector-search quality for both short and broad queries. We then employ a reranker that operates on these 512-token chunks, ensuring an optimal balance neither too coarse nor too fine for robust relevance scoring. Finally, top-ranked intermediate chunks are mapped to parent chunks (2048 tokens) to provide an LLM with sufficiently large context.
title Hierarchical Re-ranker Retriever (HRR)
topic Information Retrieval
Computation and Language
url https://arxiv.org/abs/2503.02401