Advancing Similarity Search with GenAI: A Retrieval Augmented Generation Approach
On the map: Retrieval-augmented generation → RAG pipeline design and evaluation
Abstract (arXiv)
This article introduces an innovative Retrieval Augmented Generation approach to similarity search. The proposed method uses a generative model to capture nuanced semantic information and retrieve similarity scores based on advanced context understanding. The study focuses on the BIOSSES dataset containing 100 pairs of sentences extracted from the biomedical domain, and introduces similarity search correlation results that outperform those previously attained on this dataset. Through an in-depth analysis of the model sensitivity, the research identifies optimal conditions leading to the highest similarity search accuracy: the results reveals high Pearson correlation scores, reaching specifically 0.905 at a temperature of 0.5 and a sample size of 20 examples provided in the prompt. The findings underscore the potential of generative models for semantic information retrieval and emphasize a promising research direction to similarity search.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 0 of its 15 references that are in the map. First posted on arXiv 3 Dec 2024.
Builds on
0 of 15 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Enhancing Health Information Retrieval with RAG by Prioritizing Topical Relevance and Factual Accuracy
- 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
- 2026Benchmarking Retrieval Strategies for Biomedical Retrieval-Augmented Generation: A Controlled Empirical Study
- 2024Graph-Based Retriever Captures the Long Tail of Biomedical Knowledge
- 2025Knowledge Retrieval Based on Generative AI
- 2024Beyond Benchmarks: Evaluating Embedding Model Similarity for Retrieval Augmented Generation Systems
- 2024Generative Information Retrieval Evaluation
- 2024A Comparison of Methods for Evaluating Generative IR