# Towards LLM-generated explanations for Component-based Knowledge Graph Question Answering Systems

arXiv: https://arxiv.org/abs/2508.14553 · HTML: https://mlsanity.com/paper/2508.14553/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 20 Aug 2025.

## Builds on (most cited first, 8 of 8)

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [A Survey on the Explainability of Supervised Machine Learning](https://mlsanity.com/paper/2011.07876/) (2020)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Investigating Pretrained Language Models for Graph-to-Text Generation](https://mlsanity.com/paper/2007.08426/) (2020)
- [Few-Shot NLG with Pre-Trained Language Model](https://mlsanity.com/paper/1904.09521/) (2019)
- [Explainability in Human-Agent Systems](https://mlsanity.com/paper/1904.08123/) (2019)
- [QA2Explanation: Generating and Evaluating Explanations for Question Answering Systems over Knowledge Graph](https://mlsanity.com/paper/2010.08323/) (2020)

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

- [Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study](https://mlsanity.com/paper/2512.00380/) (2025)

## Abstract (arXiv)

Over time, software systems have reached a level of complexity that makes it difficult for their developers and users to explain particular decisions made by them. In this paper, we focus on the explainability of component-based systems for Question Answering (QA). These components often conduct processes driven by AI methods, in which behavior and decisions cannot be clearly explained or justified, s.t., even for QA experts interpreting the executed process and its results is hard. To address this challenge, we present an approach that considers the components' input and output data flows as a source for representing the behavior and provide explanations for the components, enabling users to comprehend what happened. In the QA framework used here, the data flows of the components are represented as SPARQL queries (inputs) and RDF triples (outputs). Hence, we are also providing valuable insights on verbalization regarding these data types. In our experiments, the approach generates explanations while following template-based settings (baseline) or via the use of Large Language Models (LLMs) with different configurations (automatic generation). Our evaluation shows that the explanations generated via LLMs achieve high quality and mostly outperform template-based approaches according to the users' ratings. Therefore, it enables us to automatically explain the behavior and decisions of QA components to humans while using RDF and SPARQL as a context for explanations.