# GRILE: A Benchmark for Grammar Reasoning and Explanation in Romanian LLMs

arXiv: https://arxiv.org/abs/2508.14279 · HTML: https://mlsanity.com/paper/2508.14279/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 11 of 11)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language](https://mlsanity.com/paper/1905.07213/) (2019)
- [OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs](https://mlsanity.com/paper/2405.07703/) (2024)
- [Evaluating Large Language Models with Tests of Spanish as a Foreign Language: Pass or Fail?](https://mlsanity.com/paper/2409.15334/) (2024)

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

- [RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency](https://mlsanity.com/paper/2607.18756/) (2026)

## Abstract (arXiv)

LLMs (Large language models) have revolutionized NLP (Natural Language Processing), yet their pedagogical value for low-resource languages remains unclear. We present GRILE (Grammar Romanian Inference and Language Explanations) , the first open benchmark of 1,151 multiple-choice questions harvested from Romanian high-stakes exams (National Evaluation, Baccalaureate, university admissions). GRILE enables us to probe two complementary abilities of seven state-of-the-art multilingual and Romanian-specific LLMs: (i) selecting the correct answer, and (ii) producing linguistically accurate explanations. While Gemini 2.5 Pro reaches 83% accuracy, most open-weight models stay below 65%, and 48% of their explanations contain factual or pedagogical flaws according to expert review. A detailed error analysis pinpoints systematic weaknesses in morphology and in applying the latest DOOM3 orthographic norms. All data, code and a public web demo are released to catalyze future research. Our findings expose open challenges for trustworthy educational NLP in low-resource settings and establish GRILE as a new test-bed for controllable explanation generation and evaluation.