An AI-Based Adaptive Learning Platform for Multilingual and Low-Resource Educational Contexts: A Case Study on Nigeria

• URL: http://arxiv.org/abs/2608.15738v1
• Date: Sun, 16 Aug 2026 13:31:57 GMT
• Title: An AI-Based Adaptive Learning Platform for Multilingual and Low-Resource Educational Contexts: A Case Study on Nigeria
• Abstract summary: This paper presents an AI-based adaptive learning platform designed for multilingual and low-resource educational contexts.<n>The system integrates fine-tuned large language models (LLMs) within a personalised and adaptive learning framework.<n>To enhance linguistic alignment, a curated Nigerian Pidgin corpus was developed and used to fine-tune an instruction-tuned LLM.
• Score: 2.365610178729227
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Educational platforms in under-resourced and multilingual contexts, such as Nigeria, often struggle with limited personalisation, inadequate language support, and weak curriculum internationalisation, leading to reduced learner engagement and inclusivity. This paper presents an AI-based adaptive learning platform designed for multilingual and low-resource educational contexts, with a case study on Nigerian Pidgin English. The system integrates fine-tuned large language models (LLMs) within a personalised and adaptive learning (PAL) framework, addressing linguistic inclusivity and computational constraints in resource-limited environments. To enhance linguistic alignment, a curated Nigerian Pidgin corpus was developed and used to fine-tune an instruction-tuned LLM. The study further investigates model optimisation through multi-level quantisation (4-bit, 5-bit, and 8-bit), enabling systematic analysis of trade-offs between semantic fidelity and computational efficiency. Experimental evaluation combines automatic semantic metrics (BLEU, ROUGE-L, BERTScore, perplexity, lexical diversity) with human-centred cultural assessment conducted by native speakers. Results demonstrate that higher-bit quantisation improves semantic preservation and structural coherence, while lower-bit models offer reduced inference latency with minimal degradation in instructional quality. The findings establish a deployable, resource-aware intelligent learning system that balances semantic robustness, cultural relevance, and computational efficiency. This work contributes an experimentally validated framework for adapting large language models to low-resource languages while maintaining practical feasibility for scalable educational deployment.

Related papers

• Evaluating Health Misinformation in Low-Resource Languages: Integrating Small Language Models with a Culturally-Sensitive Responsible NLP Framework (Bangla as a Case Study) [0.9214837952221063]
  We propose a CALD-friendly AI-based health misinformation detector and provide a dashboard for medical professionals to analyse this misinformation.<n>We conduct experiments using a Bangla-translated health misinformation dataset to evaluate the performance of various Small Language Models (SLMs)<n>We then design and test a novel health misinformation detection framework grounded in Responsible Natural Language Processing (NLP)<n>This framework incorporates cultural sensitivity, potential for harm, and communication quality, thereby providing a holistic lens for evaluating misinformation in low-resource languages.
  arXiv  Detail & Related papers  (2026-07-14T04:34:05Z)
• Culturally Adaptive Explainable LLM Assessment for Multilingual Information Disorder: A Human-in-the-Loop Approach [0.0]
  Hybrid Intelligence Loop grounds model assessment in human-written rationales from native-speaking annotators.<n>The approach moves beyond static target-language few-shot prompting by pairing English task instructions with dynamically retrieved target-language exemplars.<n>The study evaluates span and severity prediction, the quality and cultural appropriateness of generated rationales, and model alignment across evaluator groups.
  arXiv  Detail & Related papers  (2026-03-28T18:06:14Z)
• Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency [6.943451388015595]
  Tokenization disparities pose a significant barrier to achieving equitable access to artificial intelligence.<n>This study conducts a large-scale cross-linguistic evaluation of tokenization efficiency in over 200 languages.
  arXiv  Detail & Related papers  (2025-10-14T11:14:38Z)
• Low-Resource English-Tigrinya MT: Leveraging Multilingual Models, Custom Tokenizers, and Clean Evaluation Benchmarks [6.177998679139308]
  Despite advances in Neural Machine Translation (NMT), low-resource languages like Tigrinya remain underserved.<n>This paper investigates transfer learning techniques using multilingual pretrained models to enhance translation quality for morphologically rich, low-resource languages.
  arXiv  Detail & Related papers  (2025-09-24T15:02:57Z)
• Improving Multilingual Math Reasoning for African Languages [49.27985213689457]
  We conduct experiments to evaluate different combinations of data types (translated versus synthetically generated), training stages (pre-training versus post-training), and other model adaptation configurations.<n>Our experiments focuses on mathematical reasoning tasks, using the Llama 3.1 model family as our base model.
  arXiv  Detail & Related papers  (2025-05-26T11:35:01Z)
• LIMBA: An Open-Source Framework for the Preservation and Valorization of Low-Resource Languages using Generative Models [62.47865866398233]
  This white paper proposes a framework to generate linguistic tools for low-resource languages. By addressing the data scarcity that hinders intelligent applications for such languages, we contribute to promoting linguistic diversity.
  arXiv  Detail & Related papers  (2024-11-20T16:59:41Z)
• SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition [55.2480439325792]
  Speech Meta In-Context LEarning (SMILE) is an innovative framework that combines meta-learning with speech in-context learning (SICL)<n>We show that SMILE consistently outperforms baseline methods in training-free few-shot multilingual ASR tasks.
  arXiv  Detail & Related papers  (2024-09-16T16:04:16Z)
• MoE-CT: A Novel Approach For Large Language Models Training With Resistance To Catastrophic Forgetting [53.77590764277568]
  We introduce a novel MoE-CT architecture that separates the base model's learning from the multilingual expansion process. Our design freezes the original LLM parameters, thus safeguarding its performance in high-resource languages, while an appended MoE module, trained on diverse language datasets, augments low-resource language proficiency.
  arXiv  Detail & Related papers  (2024-06-25T11:03:45Z)
• Bridging the Bosphorus: Advancing Turkish Large Language Models through Strategies for Low-Resource Language Adaptation and Benchmarking [1.3716808114696444]
  Large Language Models (LLMs) are becoming crucial across various fields, emphasizing the urgency for high-quality models in underrepresented languages. This study explores the unique challenges faced by low-resource languages, such as data scarcity, model selection, evaluation, and computational limitations.
  arXiv  Detail & Related papers  (2024-05-07T21:58:45Z)
• Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet? [82.02076369811402]
  Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. We present an extensive and systematic comparison of the three approaches, testing them on 6 high- and low-resource languages, three different NLU tasks, and a myriad of language and domain setups. Our observations show that supervised instruction tuning has the best trade-off between performance and resource requirements.
  arXiv  Detail & Related papers  (2024-03-04T10:48:13Z)
• DIALIGHT: Lightweight Multilingual Development and Evaluation of Task-Oriented Dialogue Systems with Large Language Models [76.79929883963275]
  DIALIGHT is a toolkit for developing and evaluating multilingual Task-Oriented Dialogue (ToD) systems. It features a secure, user-friendly web interface for fine-grained human evaluation at both local utterance level and global dialogue level. Our evaluations reveal that while PLM fine-tuning leads to higher accuracy and coherence, LLM-based systems excel in producing diverse and likeable responses.
  arXiv  Detail & Related papers  (2024-01-04T11:27:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.