2024/10/20 by Weichao Zhou, Jiaxin Zhang, Zhou, Weichao +7 · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #Data Management and Algorithms #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Rough Sets and Fuzzy Logic
paper · pdf · doi:10.48550/arxiv.2410.15262
openalex publication_date 2024/10/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In retrieval-augmented systems, context ranking techniques are commonly employed to reorder the retrieved contexts based on their relevance to a user query. A standard approach is to measure this relevance through the similarity between contexts and queries in the embedding space. However, such similarity often fails to capture the relevance. Alternatively, large language models (LLMs) have been used for ranking contexts. However, they can encounter scalability issues when the number of candidate contexts grows and the context window sizes of the LLMs remain constrained. Additionally, these approaches require fine-tuning LLMs with domain-specific data. In this work, we introduce a scalable ranking framework that combines embedding similarity and LLM capabilities without requiring LLM fine-tuning. Our framework uses a pre-trained LLM to hypothesize the user query based on the retrieved contexts and ranks the context based on the similarity between the hypothesized queries and the user query. Our framework is efficient at inference time and is compatible with many other retrieval and ranking techniques. Experimental results show that our method improves the ranking performance across multiple benchmarks. The complete code and data are available at https://github.com/zwc662/hyqe