arXiv subjects

Noopur Zambare

Publications and source records attributed to Noopur Zambare.

6 recordsLinked to original sources

arXiv2026

Beyond Good Intentions: When Does the Framing of Multilingual and Low-Resource NLP Research Become a Caricature?

Building language technologies and conducting NLP research for low-resource languages---particularly when led by native speakers or involving participatory research practices---are often framed as means of addressing inequality, serving local communities, and, at times, contributing to *decolonisation*. In this paper, we examine recently published NLP and ML papers, focusing on the narratives used to characterise multilinguality, low-resource languages, and underrepresented cultures. We propose a framework for analysing research framings and identify recurring rhetorical patterns that may hinder accountability and constrain equitable knowledge production for---and by---underserved communities. We further assess the evidential basis of assertions regarding community benefit and find that such statements are often weakly supported or left unsubstantiated. Although community ownership and participation are frequently presented as key objectives, our analysis, supported by statistics from the ACL Anthology, suggests that research outputs more often prioritise resource creation and benchmarking---important but distinct goals---over evidence of broader structural change. We conclude by offering practical recommendations to help authors, reviewers, and readers critically assess these assertions and avoid potentially misleading framings.

cs.CL↗

arXiv2026

Towards Fair and Efficient De-identification: Quantifying the Efficiency and Generalizability of De-identification Approaches

Large language models (LLMs) have shown strong performance on clinical de-identification, the task of identifying sensitive identifiers to protect privacy. However, previous work has not examined their generalizability between formats, cultures, and genders. In this work, we systematically evaluate fine-tuned transformer models (BERT, ClinicalBERT, ModernBERT), small LLMs (Llama 1-8B, Qwen 1.5-7B), and large LLMs (Llama-70B, Qwen-72B) at de-identification. We show that smaller models achieve comparable performance while substantially reducing inference cost, making them more practical for deployment. Moreover, we demonstrate that smaller models can be fine-tuned with limited data to outperform larger models in de-identifying identifiers drawn from Mandarin, Hindi, Spanish, French, Bengali, and regional variations of English, in addition to gendered names. To improve robustness in multi-cultural contexts, we introduce and publicly release BERT-MultiCulture-DEID, a set of de-identification models based on BERT, ClinicalBERT, and ModernBERT, fine-tuned on MIMIC with identifiers from multiple language variants. Our findings provide the first comprehensive quantification of the efficiency-generalizability trade-off in de-identification and establish practical pathways for fair and efficient clinical de-identification. Details on accessing the models are available at: https://doi.org/10.5281/zenodo.18342291

cs.CL↗

arXiv2025

Not What the Doctor Ordered: Surveying LLM-based De-identification and Quantifying Clinical Information Loss

De-identification in the healthcare setting is an application of NLP where automated algorithms are used to remove personally identifying information of patients (and, sometimes, providers). With the recent rise of generative large language models (LLMs), there has been a corresponding rise in the number of papers that apply LLMs to de-identification. Although these approaches often report near-perfect results, significant challenges concerning reproducibility and utility of the research papers persist. This paper identifies three key limitations in the current literature: inconsistent reporting metrics hindering direct comparisons, the inadequacy of traditional classification metrics in capturing errors which LLMs may be more prone to (i.e., altering clinically relevant information), and lack of manual validation of automated metrics which aim to quantify these errors. To address these issues, we first present a survey of LLM-based de-identification research, highlighting the heterogeneity in reporting standards. Second, we evaluated a diverse set of models to quantify the extent of inappropriate removal of clinical information. Next, we conduct a manual validation of an existing evaluation metric to measure the removal of clinical information, employing clinical experts to assess their efficacy. We highlight poor performance and describe the inherent limitations of such metrics in identifying clinically significant changes. Lastly, we propose a novel methodology for the detection of clinically relevant information removal.

cs.CL↗

arXiv2024

Comparing Multiclass Classification Algorithms for Financial Distress Prediction

In this study, we explore how to improve the functionality of multiclass classification algorithms. We used a benchmark dataset from Kaggle to create a framework. They have been used in a number of fields, including image recognition, natural language processing, and bioinformatics. This study is focused on the prediction of financial distress in companies in addition to the wider application in multiclass classification. Identifying businesses that are likely to experience financial distress is a crucial task in the fields of finance and risk management. Whenever a business experiences serious challenges keeping its operations going and meeting its financial responsibilities, it is said to be in financial distress. It commonly happens when a company has a sharp and sustained recession in profitability, cash flow issues, or an unsustainable level of debt.

cs.LG↗

arXiv2024

AIOptimizer - Software performance optimisation prototype for cost minimisation

This study presents AIOptimizer, a prototype for a cost-reduction-based software performance optimisation tool. The study focuses on the design elements of AIOptimizer, including user-friendliness, scalability, accuracy, and adaptability. To deliver efficient and user-focused performance optimisation solutions, it promotes the use of robust integration, continuous learning, modular design, and data collection methods. The paper also looks into AIOptimizer features including collaboration, efficiency prediction, cost optimisation suggestions, and fault diagnosis. Additionally, it introduces AIOptimizer, a recommendation engine for cost optimisation based on reinforcement learning, and examines several software development life cycle models. The goal of this research study is to showcase AIOptimizer as a prototype that continuously improves software performance and reduces costs by utilising sophisticated optimisation techniques and intelligent recommendation systems. Numerous software development life cycle models, including the Big Bang, V-, Waterfall, Iterative, and Agile models are the subject of the study. Every model has benefits and drawbacks, and the features and requirements of the project will decide how useful each is.

cs.SE↗

arXiv2024

AROhI: An Interactive Tool for Estimating ROI of Data Analytics

The cost of adopting new technology is rarely analyzed and discussed, while it is vital for many software companies worldwide. Thus, it is crucial to consider Return On Investment (ROI) when performing data analytics. Decisions on "How much analytics is needed"? are hard to answer. ROI could guide decision support on the What?, How?, and How Much? Analytics for a given problem. This work details a comprehensive tool that provides conventional and advanced ML approaches for demonstration using requirements dependency extraction and their ROI analysis as use case. Utilizing advanced ML techniques such as Active Learning, Transfer Learning and primitive Large language model: BERT (Bidirectional Encoder Representations from Transformers) as its various components for automating dependency extraction, the tool outcomes demonstrate a mechanism to compute the ROI of ML algorithms to present a clear picture of trade-offs between the cost and benefits of a technology investment.

cs.SE↗