# Selecting the Right LLM for eGov Explanations

arXiv: https://arxiv.org/abs/2504.21032 · HTML: https://mlsanity.com/paper/2504.21032/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 18 references that are in the map.
- First posted on arXiv 27 Apr 2025.

## Builds on (most cited first, 6 of 6)

- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Trust in AI: Progress, Challenges, and Future Directions](https://mlsanity.com/paper/2403.14680/) (2024)
- [AI-Augmented Business Process Management Systems: A Research Manifesto](https://mlsanity.com/paper/2201.12855/) (2022)
- [How well can a large language model explain business processes as perceived by users?](https://mlsanity.com/paper/2401.12846/) (2024)
- [The WHY in Business Processes: Discovery of Causal Execution Dependencies](https://mlsanity.com/paper/2310.14975/) (2023)

## Built on by (most cited first, 3 of 3)

- [XABPs: Towards eXplainable Autonomous Business Processes](https://mlsanity.com/paper/2507.23269/) (2025)
- [Mirror, Mirror on the Wall -- Which is the Best Model of Them All?](https://mlsanity.com/paper/2512.02043/) (2025)
- [On the Hybrid Nature of ABPMS Process Frames and its Implications on Automated Process Discovery](https://mlsanity.com/paper/2604.22455/) (2026)

## Abstract (arXiv)

The perceived quality of the explanations accompanying e-government services is key to gaining trust in these institutions, consequently amplifying further usage of these services. Recent advances in generative AI, and concretely in Large Language Models (LLMs) allow the automation of such content articulations, eliciting explanations' interpretability and fidelity, and more generally, adapting content to various audiences. However, selecting the right LLM type for this has become a non-trivial task for e-government service providers. In this work, we adapted a previously developed scale to assist with this selection, providing a systematic approach for the comparative analysis of the perceived quality of explanations generated by various LLMs. We further demonstrated its applicability through the tax-return process, using it as an exemplar use case that could benefit from employing an LLM to generate explanations about tax refund decisions. This was attained through a user study with 128 survey respondents who were asked to rate different versions of LLM-generated explanations about tax refund decisions, providing a methodological basis for selecting the most appropriate LLM. Recognizing the practical challenges of conducting such a survey, we also began exploring the automation of this process by attempting to replicate human feedback using a selection of cutting-edge predictive techniques.