# FusionMind -- Improving question and answering with external context fusion

arXiv: https://arxiv.org/abs/2401.00388 · HTML: https://mlsanity.com/paper/2401.00388/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 31 Dec 2023.

## Builds on (most cited first, 10 of 10)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering](https://mlsanity.com/paper/2101.00774/) (2021)
- [Modern Question Answering Datasets and Benchmarks: A Survey](https://mlsanity.com/paper/2206.15030/) (2022)
- [Instruction Tuned Models are Quick Learners](https://mlsanity.com/paper/2306.05539/) (2023)
- [Context-NER : Contextual Phrase Generation at Scale](https://mlsanity.com/paper/2109.08079/) (2021)
- [EDM3: Event Detection as Multi-task Text Generation](https://mlsanity.com/paper/2305.16357/) (2023)
- [LongBoX: Evaluating Transformers on Long-Sequence Clinical Tasks](https://mlsanity.com/paper/2311.09564/) (2023)

## Built on by (most cited first, 1 of 1)

- [Scaling Natural-Language Graph-Based Test Time Compute for Automated Theorem Proving](https://mlsanity.com/paper/2503.11657/) (2025)

## Abstract (arXiv)

Answering questions using pre-trained language models (LMs) and knowledge graphs (KGs) presents challenges in identifying relevant knowledge and performing joint reasoning.We compared LMs (fine-tuned for the task) with the previously published QAGNN method for the Question-answering (QA) objective and further measured the impact of additional factual context on the QAGNN performance. The QAGNN method employs LMs to encode QA context and estimate KG node importance, and effectively update the question choice entity representations using Graph Neural Networks (GNNs). We further experimented with enhancing the QA context encoding by incorporating relevant knowledge facts for the question stem. The models are trained on the OpenbookQA dataset, which contains ~6000 4-way multiple choice questions and is widely used as a benchmark for QA tasks. Through our experimentation, we found that incorporating knowledge facts context led to a significant improvement in performance. In contrast, the addition of knowledge graphs to language models resulted in only a modest increase. This suggests that the integration of contextual knowledge facts may be more impactful for enhancing question answering performance compared to solely adding knowledge graphs.