LV-ROVER-MLT: Low-Resource Maltese OCR by Synthetic Fine-Tuning and Multi-Stream Arbitration

LoRA Fine-Tuning, Frontier-LLM Prompting, and Encoder-Decoder Baselines for Low-Resource Bidirectional Sign Language Gloss Translation

UCO-UC-CICESE-Plenitas Team at MSLG-SPA 2026: Bidirectional Translation between Mexican Sign Language Glosses and Spanish Using Large Language Models

The results show that prompt-based LLM approaches can provide effective performance for low-resource sign language gloss translation.

The Lab Rats @ FinMMEval 2026 Task 2: LLM Translation and BAS-Tuned Chain-of-Thought for Multilingual Financial QA

Benchmarking Arabic--Russian Machine Translation: A Comparison of Fine-tuned NMT and Few-shot LLMs under Rich Morphology and Low Lexical Overlap

It is demonstrated that fine-tuned NMT significantly outperforms few-shot LLMs for Arabic-Russian translation under low-resource conditions.

Comparing LoRA, DoRA, and OFT for Extremely Low-Resource English–Sango Machine Translation: Adaptation Performance and Out-of-Domain Retention

Extremely low-resource machine translation poses a difficult cross-lingual adaptation problem: improving target-language performance while preserving capabilities acquired through multilingual pretraining. This study compares three mathematically distinct parameter-efficient fine-tuning (PEFT) methods—LoRA, DoRA, and o...

Every Word Presented in Context: Syntactic Coverage as Objective for Low-Resource Machine Translation with Large Language Models

Fragment-Shot Prompting is introduced, a novel few-shot prompting method that aims to retrieve examples for every word occurring in the sentence to be translated, illustrating their use and meaning in context.