Hyqe: Ranking Contexts With Hypothetical Query Embeddings

Abstract

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 q

Stats

• citations2
• S2 citations—
• github stars11
• HF likes0
• heat score5.74
• arxiv keyzhou2024hyqe

Related papers

• CEQE: Contextualized Embeddings For Query Expansion (2021)10.35
• CODER: An Efficient Framework For Improving Retrieval Through Contextual Document Embedding Reranking (2021)7.16
• Re-ranking The Context For Multimodal Retrieval Augmented Generation (2025)0.00
• Contextualized Query Embeddings For Conversational Search (2021)10.21
• Learning A Deep Listwise Context Model For Ranking Refinement (2018)15.85
• Rethinking Hybrid Retrieval: When Small Embeddings And LLM Re-ranking Beat Bigger Models (2025)0.00
• Precise Zero-shot Dense Retrieval Without Relevance Labels (2022)17.27
• Mixlm: High-throughput And Effective LLM Ranking Via Text-embedding Mix-interaction (2025)0.00