Engineering Trustworthy Retrieval-Augmented Generation for EU Electricity Market Regulation
Electronics · 10.02.2026 · 15 (4) · 749
DOI: 10.3390/electronics15040749 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 10.02.2026. Verfasst von Șener Ali und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Research, Innovation and Digitization, UEFISCDI, European Commission.
Abstract (Originalsprache)
The regulatory framework governing EU electricity markets is highly complex, fragmented across multiple normative acts and sensitive to citation accuracy and contextual completeness. While Large Language Models (LLMs) offer promising capabilities for regulatory question answering (QA), their tendency to hallucinate legal references and omit critical conditions makes them unreliable for compliance-sensitive domains. This paper presents the design of a domain-specific Retrieval-Augmented Generation (RAG) system for EU electricity market regulations, explicitly engineered to deliver source-grounded, traceable and low-hallucination answers. The answering component is based on Google’s gemini-2.5-flash model. The Open AI’s gpt-4o-mini model is responsible for both relevant document selection before building the RAG prompt and playing the judge LLM role for Retrieval Augmented Generation Assessment (RAGAS) evaluation. We build a legal corpus comprising multiple core EU regulatory acts related to REMIT and market operation and propose a regulatory QA architecture that integrates: (i) three chunking strategies (article-based, structure-aware, sliding window), (ii) two embedding models and (iii) a novel LLM-based document selection agent that restricts retrieval to the most relevant normative acts before vector search, improving contextual focus and retrieval precision. Using a fixed benchmark of regulatory questions and a reproducible evaluation protocol, we quantitatively assess system performance with RAGAS metrics and classical information-retrieval measures. While all configurations achieve strong faithfulness (up to 0.96), answer relevancy varies substantially with embedding and chunking choices. The findings confirm that retrieval engineering, particularly embedding selection, chunking strategy and pre-retrieval document filtering, has a high impact for building reliable regulatory AI systems. The sliding window strategy combined with bge-small-en-v1.5 delivered the strongest rank-sensitive retrieval performance, achieving the highest Precision@10 and NDCG@10. In contrast, article-level chunking with the same model yielded a modest improvement in Recall@10, indicating a clear trade-off between recall and precision-oriented ranking quality in legal corpora.
Förderung
- Ministry of Research, Innovation and Digitization
- UEFISCDI
- European Commission
Zitieren
APA
Ali, Ș., Oprea, S., & Bâra, A. (2026). Engineering Trustworthy Retrieval-Augmented Generation for EU Electricity Market Regulation. Electronics, 15(4), 749. https://doi.org/10.3390/electronics15040749
Vancouver
Ali Ș, Oprea S, Bâra A. Engineering Trustworthy Retrieval-Augmented Generation for EU Electricity Market Regulation. Electronics. 2026;15(4):749. doi:10.3390/electronics15040749
BibTeX
@article{Ali2026,
author = {Ali, Șener and Oprea, Simona-Vasilica and Bâra, Adela},
title = {Engineering Trustworthy Retrieval-Augmented Generation for EU Electricity Market Regulation},
journal = {Electronics},
year = {2026},
volume = {15},
number = {4},
pages = {749},
doi = {10.3390/electronics15040749}
}
EUVIMED