# Cross-lingual Relation Extraction with Large Language Models: Zero-Shot, Few-Shot, and Fine-Tuned Evaluation on Romanian

arXiv: https://arxiv.org/abs/2606.31718 · HTML: https://mlsanity.com/paper/2606.31718/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 30 Jun 2026.

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

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [The birth of Romanian BERT](https://mlsanity.com/paper/2009.08712/) (2020)
- [Introducing RONEC -- the Romanian Named Entity Corpus](https://mlsanity.com/paper/1909.01247/) (2019)
- [Multilingual Open Relation Extraction Using Cross-lingual Projection](https://mlsanity.com/paper/1503.06450/) (2015)

## Abstract (arXiv)

Relation extraction (RE) for low-resource languages is typically constrained by the lack of annotated corpora. We investigate the feasibility of cross-lingual RE for Romanian by combining automatic dataset translation with large language model (LLM) inference. We translate the SemEval-2010 Task 8 benchmark from English to Romanian using an LLM-based translation pipeline and evaluate Gemma 4 31B under zero-shot, few-shot, and QLoRA fine-tuned configurations, against four encoder baselines spanning 125M to 560M parameters: XLM- RoBERTa (base and large), Romanian BERT, and RoBERT- large. We assess two task formulations: relation classification with marked entities and end-to-end extraction. Our results show that Romanian incurs a 3 to 5 percentage point (pp) drop relative to English in prompt-only settings, that few-shot prompting provides marginal gains over zero-shot, and that QLoRA fine-tuning improves macro F1-Score by more than 22 percentage points in both languages while reducing the cross-lingual gap from 3.3 to 1.4pp. The encoder baselines come within 1-4pp of QLoRA Gemma on Romanian despite being 50-250 times smaller, with monolingual Romanian BERT at 125M parameters matching multilingual XLM-R at 278M. The case for using a 31B model for single-task RE on Romanian is therefore weak in deployment scenarios where compute matters. We release the translated dataset, evaluation code, and trained models.