# Domain-specific Question Answering with Hybrid Search

arXiv: https://arxiv.org/abs/2412.03736 · HTML: https://mlsanity.com/paper/2412.03736/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 10 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Builds on (most cited first, 3 of 3)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering](https://mlsanity.com/paper/2108.02866/) (2021)
- [Retrieval Augmented Generation for Domain-specific Question Answering](https://mlsanity.com/paper/2404.14760/) (2024)

## Built on by (most cited first, 5 of 5)

- [FinSage: A Multi-aspect RAG System for Financial Filings Question Answering](https://mlsanity.com/paper/2504.14493/) (2025)
- [SemanticCite: Citation Verification with AI-Powered Full-Text Analysis and Evidence-Based Reasoning](https://mlsanity.com/paper/2511.16198/) (2025)
- [Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering](https://mlsanity.com/paper/2508.15213/) (2025)
- [AgentHub: A Registry for Discoverable, Verifiable, and Reproducible AI Agents](https://mlsanity.com/paper/2510.03495/) (2025)
- [Nepali Passport Question Answering: A Low-Resource Dataset for Public Service Applications](https://mlsanity.com/paper/2603.13320/) (2026)

## Abstract (arXiv)

Domain specific question answering is an evolving field that requires specialized solutions to address unique challenges. In this paper, we show that a hybrid approach combining a fine-tuned dense retriever with keyword based sparse search methods significantly enhances performance. Our system leverages a linear combination of relevance signals, including cosine similarity from dense retrieval, BM25 scores, and URL host matching, each with tunable boost parameters. Experimental results indicate that this hybrid method outperforms our single-retriever system, achieving improved accuracy while maintaining robust contextual grounding. These findings suggest that integrating multiple retrieval methodologies with weighted scoring effectively addresses the complexities of domain specific question answering in enterprise settings.