# Hybrid-SQuAD: Hybrid Scholarly Question Answering Dataset

arXiv: https://arxiv.org/abs/2412.02788 · HTML: https://mlsanity.com/paper/2412.02788/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 21 references that are in the map.
- First posted on arXiv 3 Dec 2024.

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

- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Contri(e)ve: Context + Retrieve for Scholarly Question Answering](https://mlsanity.com/paper/2409.09010/) (2024)
- [Integrating SPARQL and LLMs for Question Answering over Scholarly Data Sources](https://mlsanity.com/paper/2409.18969/) (2024)

## Built on by (most cited first, 2 of 2)

- [NFDI4DS Shared Tasks for Scholarly Document Processing](https://mlsanity.com/paper/2509.22141/) (2025)
- [HANIA: Planner-Guided Multimodal Graph Evidence Selection for Grounded Question Answering](https://mlsanity.com/paper/2608.29088/) (2026)

## Abstract (arXiv)

Existing Scholarly Question Answering (QA) methods typically target homogeneous data sources, relying solely on either text or Knowledge Graphs (KGs). However, scholarly information often spans heterogeneous sources, necessitating the development of QA systems that integrate information from multiple heterogeneous data sources. To address this challenge, we introduce Hybrid-SQuAD (Hybrid Scholarly Question Answering Dataset), a novel large-scale QA dataset designed to facilitate answering questions incorporating both text and KG facts. The dataset consists of 10.5K question-answer pairs generated by a large language model, leveraging the KGs DBLP and SemOpenAlex alongside corresponding text from Wikipedia. In addition, we propose a RAG-based baseline hybrid QA model, achieving an exact match score of 69.65 on the Hybrid-SQuAD test set.