# Multimodal Hybrid Retrieval-Augmented Generation for Scientific Document Understanding using Open-Source SLMs

arXiv: https://arxiv.org/abs/2607.24799 · HTML: https://mlsanity.com/paper/2607.24799/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 11 of 11)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [EmbeddingGemma: Powerful and Lightweight Text Representations](https://mlsanity.com/paper/2509.20354/) (2025)
- [ROUGE 2.0: Updated and Improved Measures for Evaluation of Summarization Tasks](https://mlsanity.com/paper/1803.01937/) (2018)
- [Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations](https://mlsanity.com/paper/2404.18812/) (2024)
- [Optimizing Query Generation for Enhanced Document Retrieval in RAG](https://mlsanity.com/paper/2407.12325/) (2024)
- [Assessing RAG and HyDE on 1B vs. 4B-Parameter Gemma LLMs for Personal Assistants Integretion](https://mlsanity.com/paper/2506.21568/) (2025)

## Abstract (arXiv)

Large Language Models tend to hallucinate when answering domain-specific ques tions from scientific documents without prior fine-tuning. Currently, methods such as Retrieval-Augmented Generation partially solve this problem but face different challenges: limited context knowledge, difference between sparse and dense retrieval, and retrieval noise. This paper presents an Advanced Multimodal Retrieval-Augmented Generation system that aims to solve those challenges and im prove the accuracy of information extraction. The proposed architecture introduces a multimodal ingestion pipeline that leverages an open-source Vision-Language Model (Qwen2-VL-2B-Instruct) to generate textual summaries of tables and fig ures. The retrieval phase integrates HNSW-based semantic search with GIN-based lexical search, unified through Reciprocal Rank Fusion and refined using Cross Encoder reranking to minimize retrieval noise. To ensure conversational coherence across multi-turn interactions, a Query Condenser module is employed. Evaluation is conducted by independently assessing the ingestion, retrieval and generation stages using the MMLongBench benchmark, a BeIR-format synthetic dataset and the DeepEval framework. Moreover, results demonstrate a 157% improvement in retrieval quality over a Naive-RAG baseline, with only 50 ms additional la tency, while Qwen2-VL-2B-Instruct achieved results comparable to cloud-based models in BERTScore. These findings validate that open-source optimized SLMs, paired with advanced retrieval strategies, can provide competitive performance for document understanding without relying on cloud-based models.