20.500.12556/RUP-21512 Bridging the question–answer gap in retrieval-augmented generation hypothetical prompt embeddings Retrieval-Augmented Generation (RAG) systems synergize retrieval mechanisms with generative language models to enhance the accuracy and relevance of responses. However, bridging the style gap between user queries and relevant information in document text remains a persistent challenge in retrieval-augmented systems, often addressed by runtime solutions (e.g., Hypothetical Document Embeddings (HyDE)) that attempt to improve alignment but introduce extra computational overhead at query time. To address these challenges, we propose Hypothetical Prompt Embeddings (HyPE), a framework that shifts the generation of hypothetical content from query time to the indexing phase. By precomputing multiple hypothetical prompts for each data chunk and embedding the chunk in place of the prompt, HyPE transforms retrieval into a question-question matching task, bypassing the need for runtime synthetic answer generation. This approach does not introduce latency but also strengthens the alignment between queries and relevant context. Our experimental results on six common datasets show that HyPE can improve retrieval context precision by up to 42 percentage points and claim recall by up to 45 percentage points, compared to standard approaches, while remaining compatible with re-ranking, multi-vector retrieval, query decomposition, and other RAG advancements. LLM hypothetical prompt embedding Retrieval-Augmented Generation (RAG) umetna inteligenca HyPE HyDE true false true Angleški jezik Slovenski jezik Članek v reviji 2025-08-04 10:01:40 2025-08-04 10:01:41 2025-08-05 03:02:40 0000-00-00 00:00:00 2025 0 0 str. 129952-129961 Vol. 13 2025 0000-00-00 NiDoloceno NiDoloceno apc 0000-00-00 0000-00-00 2025-07-15 004.8 2169-3536 10.1109/ACCESS.2025.3589499 244701955 RAZ_Vake_Domen_2025.pdf RAZ_Vake_Domen_2025.pdf 1 A642E181DB07BC4D6B4A0B0058B6E8EE 26b9f35e6953f81be9e82ea01fe0afac3dd9af2dd30c1964ea0e97787e4d51c7 745fdfca-7109-11f0-8f0b-005056ac49c0 https://repozitorij.upr.si/Dokument.php?lang=slv&id=31277 https://ieeexplore.ieee.org/document/11080443 0 11bf8215-710a-11f0-8f0b-005056ac49c0 https://repozitorij.upr.si/Dokument.php?lang=slv&id=31278 Fakulteta za matematiko, naravoslovje in informacijske tehnologije 0 0 0