Aliya Nugumanova

Dr. Aliya Nugumanova

Big Data and Blockchain Technologies, Astana IT University, Nur-Sultan, Astana, Kazakhstan
orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 September 2024 in Big Data and Cognitive Computing
Verified
Journal Article
Open access
PDF file
AMAigerim Mansurova
Aigerim Mansurova
AMAiganym Mansurova
Aiganym Mansurova
ANAliya Nugumanova
Aliya Nugumanova
Large language models (LLMs) can store factual knowledge within their parameters and have achieved superior results in question-answering tasks. However, challenges persist in providing provenance for their decisions and keeping their knowledge up to date. Some approaches aim to address these challenges by combining external knowledge with parametric memory. In contrast, our proposed QA-RAG solution relies solely on the data stored within an external knowledge base, specifically a dense vector index database. In this paper, we compare RAG configurations using two LLMs—Llama 2b and 13b—systematically examining their performance in three key RAG capabilities: noise robustness, knowledge gap detection, and external truth integration. The evaluation reveals that while our approach achieves an accuracy of 83.3%, showcasing its effectiveness across all baselines, the model still struggles significantly in terms of external truth integration. These findings suggest that considerable work is still required to fully leverage RAG in question-answering tasks.

11 May 2023 in Data
Verified
Journal Article
Open access
PDF file
AMAlmasbek Maulit
Almasbek Maulit
ANAliya Nugumanova
Aliya Nugumanova
YBYerzhan Baiburin
Yerzhan Baiburin
YBYerzhan Baiburin
Yerzhan Baiburin
Maxim Y. SutulaMaxim Y. Sutula
Maxim Y. Sutula
This study introduces a dataset of crop imagery captured during the 2022 growing season in the Eastern Kazakhstan region. The images were acquired using a multispectral camera mounted on an unmanned aerial vehicle (DJI Phantom 4). The agricultural land, encompassing 27 hectares and cultivated with wheat, barley, and soybean, was subjected to five aerial multispectral photography sessions throughout the growing season. This facilitated thorough monitoring of the most important phenological stages of crop development in the experimental design, which consisted of 27 plots, each covering one hectare. The collected imagery underwent enhancement and expansion, integrating a sixth band that embodies the normalized difference vegetation index (NDVI) values in conjunction with the original five multispectral bands (Blue, Green, Red, Red Edge, and Near Infrared Red). This amplification enables a more effective evaluation of vegetation health and growth, rendering the enriched dataset a valuable resource for the progression and validation of crop monitoring and yield prediction models, as well as for the exploration of precision agriculture methodologies.

30 September 2023 in Scientific Journal of Astana IT University
Verified
Journal Article
Open access
PDF file
AMAigerim Mansurova
Aigerim Mansurova
ANAliya Nugumanova
Aliya Nugumanova
ZMZhansaya Makhambetova
Zhansaya Makhambetova
Large Language Models (LLMs), such as ChatGPT, have transformed the field of natural language processing with their capacity for language comprehension and generation of human-like, fluent responses for many downstream tasks. Despite their impressive capabilities, they often fall short in domain-specific and knowledge-intensive domains due to a lack of access to relevant data. Moreover, most state-of-art LLMs lack transparency as they are often accessible only through APIs. Furthermore, their application in critical real-world scenarios is hindered by their proclivity to produce hallucinated information and inability to leverage external knowledge sources. To address these limitations, we propose an innovative system that enhances LLMs by integrating them with an external knowledge management module. The system allows LLMs to utilize data stored in vector databases, providing them with relevant information for their responses. Additionally, it enables them to retrieve information from the Internet, further broadening their knowledge base. The research approach circumvents the need to retrain LLMs, which can be a resource-intensive process. Instead, it focuses on making more efficient use of existing models. Preliminary results indicate that the system holds promise for improving the performance of LLMs in domain-specific and knowledge-intensive tasks. By equipping LLMs with real-time access to external data, it is possible to harness their language generation capabilities more effectively, without the need to continually strive for larger models.

30 October 2025 in Information
Verified
Journal Article
Open access
PDF file
AMAigerim Mansurova
Aigerim Mansurova
Arailym TleubayevaArailym Tleubayeva
Arailym Tleubayeva
ANAliya Nugumanova
Aliya Nugumanova
ASAday Shomanov
Aday Shomanov
SSSadi Evren Seker
Sadi Evren Seker
This paper presents a systematic evaluation of large language models (LLMs) and retrieval-augmented generation (RAG) approaches for question answering (QA) in the low-resource Kazakh language. We assess the performance of existing proprietary (GPT-4o, Gemini 2.5-flash) and open-source Kazakh-oriented models (KazLLM-8B, Sherkala-8B, Irbis-7B) across closed-book and RAG settings. Within a three-stage evaluation framework we benchmark retriever quality, examine LLM abilities such as knowledge-gap detection, external truth integration and context grounding, and measures gains from realistic end-to-end RAG pipelines. Our results show a clear pattern: proprietary models lead in closed-book QA, but RAG narrows the gap substantially. Under the Ideal RAG setting, KazLLM-8B improves from its closed-book baseline of 0.427 to reach answer correctness of 0.867, closely matching GPT-4o’s score of 0.869. In the end-to-end RAG setup, KazLLM-8B paired with Snowflake retriever achieved answer correctness up to 0.754, surpassing GPT-4o’s best score of 0.632. Despite improvements, RAG outcomes show an inconsistency: high retrieval metrics do not guarantee high QA system accuracy. The findings highlight the importance of retrievers and context grounding strategies in enabling open-source Kazakh models to deliver competitive QA performance in a low-resource setting.

23 July 2025 in Data
Verified
Journal Article
Open access
PDF file
AMAigerim Mansurova
Aigerim Mansurova
AMAigerim Mussina
Aigerim Mussina
SASanzhar Aubakirov
Sanzhar Aubakirov
ANAliya Nugumanova
Aliya Nugumanova
Didar YedilkhanDidar Yedilkhan
Didar Yedilkhan
The data descriptor introduces an open, high-resolution dataset of real-world bus operations in Astana, Kazakhstan, captured from GPS trajectories between July and September 2024. The data covers three high-frequency routes and have been processed into a GTFS format, enabling direct use with existing transit modeling tools. Unlike typical static GTFS feeds, this dataset provides empirically observed dwell times, run times, and travel times, offering a detailed snapshot of operational variability in urban bus systems. The dataset supports applications in machine learning–based travel time prediction, timetable optimization, and transit reliability analysis, especially in settings where live feeds are unavailable. By releasing this dataset publicly, we aim to promote transparent, data-driven transport research in emerging urban contexts.

1 June 2016 in Международный журнал "Программные продукты и системы"
Verified
Journal Article
Closed access
ANAliya Nugumanova
Aliya Nugumanova
IBIgor Bessmertny
Igor Bessmertny
PPPavel Pecina
Pavel Pecina
ЕBЕ.M. Baiburin
Е.M. Baiburin