Multilingual models are parameter-efficient and especially effective in improving low-resource languages by leveraging crosslingual transfer. Despite recent advance in massive multilingual translation with ever-growing model and data, how to effectively train multilingual models has not been well understood. In this paper, we show that a common situation in multilingual training, data imbalance among languages, poses optimization tension between high resource and low resource languages where the found multilingual solution is often sub-optimal for low resources. We show that common training method which upsamples low resources can not robustly optimize population loss with risks of either underfitting high resource languages or overfitting low resource ones. Drawing on recent findings on the geometry of loss landscape and its effect on generalization, we propose a principled optimization algorithm, Curvature Aware Task Scaling (CATS), which adaptively rescales gradients from different tasks with a meta objective of guiding multilingual training to low-curvature neighborhoods with uniformly low loss for all languages. We ran experiments on common benchmarks (TED, WMT and OPUS-100) with varying degrees of data imbalance. CATS effectively improved multilingual optimization and as a result demonstrated consistent gains on low resources ($+0.8$ to $+2.2$ BLEU) without hurting high resources. In addition, CATS is robust to overparameterization and large batch size training, making it a promising training method for massive multilingual models that truly improve low resource languages.

Linguistic diversity across the world creates a disparity with the availability of good quality digital language resources thereby restricting the technological benefits to majority of human population. The lack or absence of data resources makes it difficult to perform NLP tasks for low-resource languages. This paper presents a novel scalable and fully automated methodology to extract bilingual parallel corpora from newspaper articles using image and text analytics. We validate our approach by building parallel data corpus for two different language combinations and demonstrate the value of this dataset through a downstream task of machine translation and improve over the current baseline by close to 3 BLEU points.

Multilingual Large Language Models (LLMs) are increasingly used worldwide, making it essential to ensure they are free from gender bias to prevent representational harm. While prior studies have examined such biases in high-resource languages, low-resource languages remain understudied. In this paper, we propose a template-based probing methodology, validated against real-world data, to uncover gender stereotypes in LLMs. As part of this framework, we introduce the Domain-Specific Gender Skew Index (DS-GSI), a metric that quantifies deviations from gender parity. We evaluate four prominent models, GPT-4o mini, DeepSeek R1, Gemini 2.0 Flash, and Qwen QwQ 32B, across four semantic domains, focusing on Persian, a low-resource language with distinct linguistic features. Our results show that all models exhibit gender stereotypes, with greater disparities in Persian than in English across all domains. Among these, sports reflect the most rigid gender biases. This study underscores the need for inclusive NLP practices and provides a framework for assessing bias in other low-resource languages.

In this paper,we explore the application of Back translation (BT) as a semi-supervised technique to enhance Neural Machine Translation(NMT) models for the English-Luganda language pair, specifically addressing the challenges faced by low-resource languages. The purpose of our study is to demonstrate how BT can mitigate the scarcity of bilingual data by generating synthetic data from monolingual corpora. Our methodology involves developing custom NMT models using both publicly available and web-crawled data, and applying Iterative and Incremental Back translation techniques. We strategically select datasets for incremental back translation across multiple small datasets, which is a novel element of our approach. The results of our study show significant improvements, with translation performance for the English-Luganda pair exceeding previous benchmarks by more than 10 BLEU score units across all translation directions. Additionally, our evaluation incorporates comprehensive assessment metrics such as SacreBLEU, ChrF2, and TER, providing a nuanced understanding of translation quality. The conclusion drawn from our research confirms the efficacy of BT when strategically curated datasets are utilized, establishing new performance benchmarks and demonstrating the potential of BT in enhancing NMT models for low-resource languages.

Generative Artificial Intelligence (GenAI), particularly Large Language Models (LLMs), has significantly advanced Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), which involves identifying entities like person, location, and organization names in text. LLMs are especially promising for low-resource languages due to their ability to learn from limited data. However, the performance of GenAI models for Nepali, a low-resource language, has not been thoroughly evaluated. This paper investigates the application of state-of-the-art LLMs for Nepali NER, conducting experiments with various prompting techniques to assess their effectiveness. Our results provide insights into the challenges and opportunities of using LLMs for NER in low-resource settings and offer valuable contributions to the advancement of NLP research in languages like Nepali.

LLMs are predominantly trained on English data, which leads to a significant drop in performance on low-resource languages. Understanding how LLMs handle these languages is crucial for improving their effectiveness. This study focuses on Urdu as a use case for exploring the challenges faced by LLMs in processing low-resource languages. LLMs primarily reason in English when prompted in another language, with the final layers acting as translators to convert the English response into the target language. This study finds that even for low-resource languages, the internal latent response of LLMs in English is quite coherent; however, the translation features are lossy and result in poor translations, leading to reduced performance. By mechanistically removing these translation features and using a separate translation model to translate the internal latent response of LLM, the performance of LLMs improves significantly while also preserving the cultural nuances of the input in low-resource languages.

Multilingual models are parameter-efficient and especially effective in improving low-resource languages by leveraging crosslingual transfer. Despite recent advance in massive multilingual translation with ever-growing model and data, how to effectively train multilingual models has not been well understood. In this paper, we show that a common situation in multilingual training, data imbalance among languages, poses optimization tension between high resource and low resource languages where the found multilingual solution is often sub-optimal for low resources. We show that common training method which upsamples low resources can not robustly optimize population loss with risks of either underfitting high resource languages or overfitting low resource ones. Drawing on recent findings on the geometry of loss landscape and its effect on generalization, we propose a principled optimization algorithm, Curvature Aware Task Scaling (CATS), which adaptively rescales gradients from different tasks with a meta objective of guiding multilingual training to low-curvature neighborhoods with uniformly low loss for all languages.

Box 30197 Nairobi 00100, Kenya eamiriti@uonbi.ac.ke Abstract Processing low-resource languages, such as Kiswahili, using machine learning is difficult due to lack of adequate training data. However, such low-resource languages are still important for human communication and are already in daily use and users need practical machine processing tasks such as summarization, disambiguation and even question answering (QA). One method of processing such languages, while bypassing the need for training data, is the use semantic networks. Some low resource languages, such as Kiswahili, are of the subject-verb-object (SVO) structure, and similarly semantic networks are a triple of subject-predicate-object, hence SVO parts of speech tags can map into a semantic network triple. An algorithm to process raw natural language text and map it into a semantic network is therefore necessary and desirable in structuring low resource languages texts. This algorithm tested on the Kiswahili QA task with upto 78.6% exact match. Highlights Languages, both low and high-resource are important for communication. Low resource languages lack vast data repositories necessary for machine learning. Use of language part of speech tags can create meaning from the language. An algorithm can create semantic networks out of the language parts of speech. The semantic network of the language can do practical tasks such as QA.