# Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networks

arXiv: https://arxiv.org/abs/2305.01548 · HTML: https://mlsanity.com/paper/2305.01548/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2023.

## Built on by (most cited first, 9 of 9)

- [A Survey of Conversational Search](https://mlsanity.com/paper/2410.15576/) (2024)
- [CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era](https://mlsanity.com/paper/2412.18702/) (2024)
- [RAG-based Question Answering over Heterogeneous Data and Text](https://mlsanity.com/paper/2412.07420/) (2024)
- [Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2511.20940/) (2025)
- [The ReQAP System for Question Answering over Personal Information](https://mlsanity.com/paper/2508.06880/) (2025)
- [A Graph-to-Text Approach to Knowledge-Grounded Response Generation in Human-Robot Interaction](https://mlsanity.com/paper/2311.16137/) (2023)
- [LAMP: Learnable Meta-Path Guided Adversarial Contrastive Learning for Heterogeneous Graphs](https://mlsanity.com/paper/2409.06323/) (2024)
- [FHGE: A Fast Heterogeneous Graph Embedding with Ad-hoc Meta-paths](https://mlsanity.com/paper/2502.16281/) (2025)
- [ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining](https://mlsanity.com/paper/2511.22866/) (2025)

## Abstract (arXiv)

In conversational question answering, users express their information needs through a series of utterances with incomplete context. Typical ConvQA methods rely on a single source (a knowledge base (KB), or a text corpus, or a set of tables), thus being unable to benefit from increased answer coverage and redundancy of multiple sources. Our method EXPLAIGNN overcomes these limitations by integrating information from a mixture of sources with user-comprehensible explanations for answers. It constructs a heterogeneous graph from entities and evidence snippets retrieved from a KB, a text corpus, web tables, and infoboxes. This large graph is then iteratively reduced via graph neural networks that incorporate question-level attention, until the best answers and their explanations are distilled. Experiments show that EXPLAIGNN improves performance over state-of-the-art baselines. A user study demonstrates that derived answers are understandable by end users.