arXiv subjects

Kuldeep Singh

Publications and source records attributed to Kuldeep Singh.

At least 19 recordsLinked to original sources

arXiv2026

pro-team at LLMs4OL 2026 Tasks Flagship and Reuse: Retrieval-Augmented Generation and Vocabulary-Constrained Filtering for Ontology Learning

Ontology learning from text remains challenging despite significant progress in Large Language Models (LLMs), which can hallucinate domain terms, produce inconsistent formats, and favor hierarchical over associative relations. In the LLMs4OL 2026 Challenge, we address both the End-to-End Flagship Task (Task A) and Ontology Extension Reuse Task (Task B) using an offline retrieval-augmented few-shot prompting pipeline. Our system employs Qwen2.5-14B-Instruct with all-MiniLM-L6-v2 for demonstration retrieval, selecting the top-5 examples for Task A and top-2 for Task B. A left-truncated context-windowing strategy preserves task instructions within long prompts. For Task B, generated triples undergo deterministic vocabulary-constrained filtering, retaining triples when at least one endpoint belongs to the sample's closed term/type vocabulary and removing duplicates of the initial ontology. The approach achieves Semantic Graph Similarity of 0.8692, Term-Typing F1 of 0.9200, and Taxonomy Discovery F1 of 0.8540 on Task B, while Task A achieves 0.7416 Semantic Graph Similarity. However, no non-taxonomic relations are extracted, highlighting limitations of closed, taxonomy-oriented relation vocabularies.

cs.AI↗

arXiv2026

Position: Avoid Overstretching LLMs for every Enterprise Task

Enterprise workloads are dominated by deterministic, structured, and knowledge-dependent tasks operating under strict cost, latency, and reliability constraints. While these are often addressed through large language model (LLM) deployment or distillation into smaller models, we argue this is inefficient, unreliable, and misaligned with enterprise task structures. Instead, AI systems should treat language models as interfaces rather than monolithic engines, externalizing knowledge and computation into dedicated components for greater reliability, scalability, and transparency. Our theoretical evidences show that finite-capacity models cannot fully capture the breadth of knowledge required for enterprise tasks, creating inherent limits to efficiency and interpretability. Building on this, we take the position that language models should primarily be used for structured extraction in deterministic enterprise workflows, while computation and storage are delegated to knowledge bases and symbolic procedures. We formally demonstrate that such modular architectures are more reliable and maintainable than monolithic frameworks, offering a sustainable foundation for enterprise tasks.

cs.AI↗

arXiv2026

Agent-Agnostic Evaluation of SQL Accuracy in Production Text-to-SQL Systems

Text-to-SQL (T2SQL) evaluation in production environments poses fundamental challenges that existing benchmarks do not address. Current evaluation methodologies whether rule-based SQL matching or schema-dependent semantic parsers assume access to ground-truth queries and structured database schema, constraints that are rarely satisfied in real-world deployments. This disconnect leaves production T2SQL agents largely unevaluated beyond developer-time testing, creating silent quality degradation with no feedback mechanism for continuous improvement. We present STEF (Schema-agnostic Text-to-SQL Evaluation Framework), a production-native evaluation system that operates exclusively on natural language inputs the user question, an enriched reformulation, and the generated SQL without requiring database schema or reference queries. STEF extracts semantic specifications from both natural language and SQL representations, performs normalized feature alignment, and produces an interpretable 0 to 100 accuracy score via a composite metric that encompasses filter alignment, semantic verdict, and confidence of the evaluator. Key contributions include: enriched question quality validation as a first-class evaluation signal, configurable application-specific rule injection via prompt templating, and production-robust normalization handling GROUP BY tolerance, ORDER BY defaults, and LIMIT heuristics. Empirical results demonstrate that STEF enables continuous production monitoring and agent improvement feedback loops without schema dependency, making structured query evaluation viable at scale for the first time.

cs.AI↗

arXiv2026

Online learning of smooth functions on $\mathbb{R}$

We study adversarial online learning of real-valued functions on $\mathbb{R}$. In each round the learner is queried at $x_t\in\mathbb{R}$, predicts $\hat y_t$, and then observes the true value $f(x_t)$; performance is measured by cumulative $p$-loss $\sum_{t\ge 1}|\hat y_t-f(x_t)|^p$. For the class \[ \mathcal{G}_q=\Bigl\{f:\mathbb{R}\to\mathbb{R}\ \text{absolutely continuous}:\ \int_{\mathbb{R}}|f'(x)|^q\,dx\le 1\Bigr\}, \] we show that the standard model becomes ill-posed on $\mathbb{R}$: for every $p\ge 1$ and $q>1$, an adversary can force infinite loss. Motivated by this obstruction, we analyze three modified learning scenarios that limit the influence of queries that are far from previously observed inputs. In Scenario 1 the adversary must choose each new query within distance $1$ of some past query. In Scenario 2 the adversary may query anywhere, but the learner is penalized only on rounds whose query lies within distance $1$ of a past query. In Scenario 3 the loss in round $t$ is multiplied by a weight $g(\min_{j<t}|x_t-x_j|)$. We obtain sharp characterizations for Scenarios 1-2 in several regimes. For Scenario 3 we identify a clean threshold phenomenon: if $g$ decays too slowly, then the adversary can force infinite weighted loss. In contrast, for rapidly decaying weights such as $g(z)=e^{-cz}$ we obtain finite and sharp guarantees in the quadratic case $p=q=2$. Finally, we study a natural multivariable slice generalization $\mathcal{G}_{q,d}$ of $\mathcal{G}_q$ on $\mathbb{R}^d$ and show a sharp dichotomy: while the one-dimensional case admits finite opt-values in certain regimes, for every $d\ge 2$ the slice class $\mathcal{G}_{q,d}$ is too permissive, and even under Scenarios 1-3 an adversary can force infinite loss.

cs.LG↗

arXiv2025

Spin-photon Qubits for Scalable Quantum Network

Solid-state quantum light sources offer a scalable pathway for interfacing stationary spin qubits with flying photonic qubits, forming the backbone of future quantum networks. Telecom-band spin-photonic qubits, operating in the 1260-1675 nm wavelength range, are particularly well-suited for long-distance quantum communication due to minimal loss in standard optical fibers. Achieving scalability, however, hinges on fulfilling several stringent criteria: coherent spin-state control, deterministic and indistinguishable single-photon emission, and integration with nanophotonic structures that enhance radiative properties, such as lifetime, coherence, and photon indistinguishability. This study explores the state-of-the-art spin-photonic qubits across solid-state platforms, including diamond color centers, silicon carbide defect centers, quantum dots, and two-dimensional materials. Special attention is given to silicon-based emitters, particularly G, T, C- and Ci-centers, which promise monolithic integration with complementary metal-oxide-semiconductor (CMOS) technology and telecom-band operation. We classify these systems based on spin-photon interface availability, CMOS process compatibility, and emitter scalability. We also discuss recent advances in cavity quantum electrodynamics (cQED), including Purcell enhancement and quality factor engineering in integrated photonic (circuits) environments. The work highlights emerging demonstrations of quantum networking over metropolitan scales and outlines the trajectory toward chip-scale quantum photonic integrated circuits (QPICs). It combines deterministic emitter creation, coherent spin manipulation, and quantum information processing. These developments pave the way for global quantum networks, enabling secure communication, distributed quantum computing, and quantum-enhanced sensing.

quant-ph↗

arXiv2025

NutriScreener: Retrieval-Augmented Multi-Pose Graph Attention Network for Malnourishment Screening

Child malnutrition remains a global crisis, yet existing screening methods are laborious and poorly scalable, hindering early intervention. In this work, we present NutriScreener, a retrieval-augmented, multi-pose graph attention network that combines CLIP-based visual embeddings, class-boosted knowledge retrieval, and context awareness to enable robust malnutrition detection and anthropometric prediction from children's images, simultaneously addressing generalizability and class imbalance. In a clinical study, doctors rated it 4.3/5 for accuracy and 4.6/5 for efficiency, confirming its deployment readiness in low-resource settings. Trained and tested on 2,141 children from AnthroVision and additionally evaluated on diverse cross-continent populations, including ARAN and an in-house collected CampusPose dataset, it achieves 0.79 recall, 0.82 AUC, and significantly lower anthropometric RMSEs, demonstrating reliable measurement in unconstrained pediatric settings. Cross-dataset results show up to 25% recall gain and up to 3.5 cm RMSE reduction using demographically matched knowledge bases. NutriScreener offers a scalable and accurate solution for early malnutrition detection in low-resource environments.

cs.CV↗

arXiv2025

A Modified Dielectric Contrast based Integral Equation for 2D TE Scattering by Inhomogeneous Domains

This work presents a modified domain integral equation approach for the forward problem of TE scattering, employing a modified definition of dielectric contrast and discretizing the electric field density using Rao-Wilton-Glisson (RWG) basis functions. The proposed formulation mitigates the numerical challenges introduced by the gradient-divergence operator in traditional electric field-based vector formulations. The use of RWG basis functions over triangular meshes enhances geometric conformity, ensures tangential continuity across dielectric interfaces, and facilitates the application of well known singularity extraction techniques for numerical accuracy. Validation through numerical experiments on a two-layered dielectric cylinder demonstrates excellent agreement between computed and analytical scattered fields. Convergence studies confirm improving solution accuracy with mesh refinement indicating robustness with respect to discretization without increasing the iterations.

math.NA↗

arXiv2025

Comparative Analysis of AI Agent Architectures for Entity Relationship Classification

Entity relationship classification remains a challenging task in information extraction, especially in scenarios with limited labeled data and complex relational structures. In this study, we conduct a comparative analysis of three distinct AI agent architectures designed to perform relation classification using large language models (LLMs). The agentic architectures explored include (1) reflective self-evaluation, (2) hierarchical task decomposition, and (3) a novel multi-agent dynamic example generation mechanism, each leveraging different modes of reasoning and prompt adaptation. In particular, our dynamic example generation approach introduces real-time cooperative and adversarial prompting. We systematically compare their performance across multiple domains and model backends. Our experiments demonstrate that multi-agent coordination consistently outperforms standard few-shot prompting and approaches the performance of fine-tuned models. These findings offer practical guidance for the design of modular, generalizable LLM-based systems for structured relation extraction. The source codes and dataset are available at https://github.com/maryambrj/ALIEN.git.

cs.CL↗

arXiv2025

Ethical AI in the Healthcare Sector: Investigating Key Drivers of Adoption through the Multi-Dimensional Ethical AI Adoption Model (MEAAM)

The adoption of Artificial Intelligence (AI) in the healthcare service industry presents numerous ethical challenges, yet current frameworks often fail to offer a comprehensive, empirical understanding of the multidimensional factors influencing ethical AI integration. Addressing this critical research gap, this study introduces the Multi-Dimensional Ethical AI Adoption Model (MEAAM), a novel theoretical framework that categorizes 13 critical ethical variables across four foundational dimensions of Ethical AI Fair AI, Responsible AI, Explainable AI, and Sustainable AI. These dimensions are further analyzed through three core ethical lenses: epistemic concerns (related to knowledge, transparency, and system trustworthiness), normative concerns (focused on justice, autonomy, dignity, and moral obligations), and overarching concerns (highlighting global, systemic, and long-term ethical implications). This study adopts a quantitative, cross-sectional research design using survey data collected from healthcare professionals and analyzed via Partial Least Squares Structural Equation Modeling (PLS-SEM). Employing PLS-SEM, this study empirically investigates the influence of these ethical constructs on two outcomes Operational AI Adoption and Systemic AI Adoption. Results indicate that normative concerns most significantly drive operational adoption decisions, while overarching concerns predominantly shape systemic adoption strategies and governance frameworks. Epistemic concerns play a facilitative role, enhancing the impact of ethical design principles on trust and transparency in AI systems. By validating the MEAAM framework, this research advances a holistic, actionable approach to ethical AI adoption in healthcare and provides critical insights for policymakers, technologists, and healthcare administrators striving to implement ethically grounded AI solutions.

cs.AI↗

arXiv2025

Transformer-Driven Modeling of Variable Frequency Features for Classifying Student Engagement in Online Learning

The COVID-19 pandemic and the internet's availability have recently boosted online learning. However, monitoring engagement in online learning is a difficult task for teachers. In this context, timely automatic student engagement classification can help teachers in making adaptive adjustments to meet students' needs. This paper proposes EngageFormer, a transformer based architecture with sequence pooling using video modality for engagement classification. The proposed architecture computes three views from the input video and processes them in parallel using transformer encoders; the global encoder then processes the representation from each encoder, and finally, multi layer perceptron (MLP) predicts the engagement level. A learning centered affective state dataset is curated from existing open source databases. The proposed method achieved an accuracy of 63.9%, 56.73%, 99.16%, 65.67%, and 74.89% on Dataset for Affective States in E-Environments (DAiSEE), Bahcesehir University Multimodal Affective Database-1 (BAUM-1), Yawning Detection Dataset (YawDD), University of Texas at Arlington Real-Life Drowsiness Dataset (UTA-RLDD), and curated learning-centered affective state dataset respectively. The achieved results on the BAUM-1, DAiSEE, and YawDD datasets demonstrate state-of-the-art performance, indicating the superiority of the proposed model in accurately classifying affective states on these datasets. Additionally, the results obtained on the UTA-RLDD dataset, which involves two-class classification, serve as a baseline for future research. These results provide a foundation for further investigations and serve as a point of reference for future works to compare and improve upon.

cs.CV↗

arXiv2025

Construal Level and Cognitive Reflection in Newsvendor Games: Unveiling the Influence of Individual Heterogeneity on Decision-Making

During the last decade, scholars have studied the behavior of decision-making in newsvendor settings and have identified numerous behavior patterns for deviating from normative behavior. However, there is a dearth of research which have examined the influence of individual heterogeneity on decision-making in newsvendor settings. This study examines the level of construal (Abstract and concrete) using construal level theory (CLT) on performance in newsvendor games. In addition, this study measures the cognitive reflection of individuals using cognitive reflection test (CRT) ex-ante to analyze the true impact of how people construe a problem and its impact on their decision-making.

physics.soc-ph↗

arXiv2025

Determinants of Human Development Index (HDI): A Regression Analysis of Economic and Social Indicators

This study aims to investigate the factors influencing the Human Development Index (HDI). Five variables-GDP per capita, health expenditure, education expenditure, infant mortality rate (per 1,000 live births), and average years of schooling-were analyzed to develop a regression model assessing their impact on HDI. The results indicate that GDP per capita, infant mortality rate, and average years of schooling are significant predictors of HDI. Specifically, the study finds a positive relationship between GDP per capita and average years of schooling with HDI, while infant mortality rate is negatively associated with HDI.

cs.CY↗

arXiv2025

The Dead Internet Theory: A Survey on Artificial Interactions and the Future of Social Media

The Dead Internet Theory (DIT) suggests that much of today's internet, particularly social media, is dominated by non-human activity, AI-generated content, and corporate agendas, leading to a decline in authentic human interaction. This study explores the origins, core claims, and implications of DIT, emphasizing its relevance in the context of social media platforms. The theory emerged as a response to the perceived homogenization of online spaces, highlighting issues like the proliferation of bots, algorithmically generated content, and the prioritization of engagement metrics over genuine user interaction. AI technologies play a central role in this phenomenon, as social media platforms increasingly use algorithms and machine learning to curate content, drive engagement, and maximize advertising revenue. While these tools enhance scalability and personalization, they also prioritize virality and consumption over authentic communication, contributing to the erosion of trust, the loss of content diversity, and a dehumanized internet experience. This study redefines DIT in the context of social media, proposing that the commodification of content consumption for revenue has taken precedence over meaningful human connectivity. By focusing on engagement metrics, platforms foster a sense of artificiality and disconnection, underscoring the need for human-centric approaches to revive authentic online interaction and community building.

cs.CY↗

arXiv2024

Travelling wave solutions of an equation of Harry Dym type arising in the Black-Scholes framework

The Black-Scholes framework is crucial in pricing a vast number of financial instruments that permeate the complex dynamics of world markets. Associated with this framework, we consider a second-order differential operator $L(x, {\partial_x}) := v^2(x,t) (\partial_x^2 -\partial_x)$ that carries a variable volatility term $v(x,t)$ and which is dependent on the underlying log-price $x$ and a time parameter $t$ motivated by the celebrated Dupire local volatility model. In this context, we ask and answer the question of whether one can find a non-linear evolution equation derived from a zero-curvature condition for a time-dependent deformation of the operator $L$. The result is a variant of the Harry Dym equation for which we can then find a family of travelling wave solutions. This brings in extensive machinery from soliton theory and integrable systems. As a by-product, it opens up the way to the use of coherent structures in financial-market volatility studies.

math.NA↗

arXiv2024

User-Aware Multilingual Abusive Content Detection in Social Media

Despite growing efforts to halt distasteful content on social media, multilingualism has added a new dimension to this problem. The scarcity of resources makes the challenge even greater when it comes to low-resource languages. This work focuses on providing a novel method for abusive content detection in multiple low-resource Indic languages. Our observation indicates that a post's tendency to attract abusive comments, as well as features such as user history and social context, significantly aid in the detection of abusive content. The proposed method first learns social and text context features in two separate modules. The integrated representation from these modules is learned and used for the final prediction. To evaluate the performance of our method against different classical and state-of-the-art methods, we have performed extensive experiments on SCIDN and MACI datasets consisting of 1.5M and 665K multilingual comments, respectively. Our proposed method outperforms state-of-the-art baseline methods with an average increase of 4.08% and 9.52% in F1-scores on SCIDN and MACI datasets, respectively.

cs.SI↗

arXiv2024

FinQAPT: Empowering Financial Decisions with End-to-End LLM-driven Question Answering Pipeline

Financial decision-making hinges on the analysis of relevant information embedded in the enormous volume of documents in the financial domain. To address this challenge, we developed FinQAPT, an end-to-end pipeline that streamlines the identification of relevant financial reports based on a query, extracts pertinent context, and leverages Large Language Models (LLMs) to perform downstream tasks. To evaluate the pipeline, we experimented with various techniques to optimize the performance of each module using the FinQA dataset. We introduced a novel clustering-based negative sampling technique to enhance context extraction and a novel prompting method called Dynamic N-shot Prompting to boost the numerical question-answering capabilities of LLMs. At the module level, we achieved state-of-the-art accuracy on FinQA, attaining an accuracy of 80.6%. However, at the pipeline level, we observed decreased performance due to challenges in extracting relevant context from financial reports. We conducted a detailed error analysis of each module and the end-to-end pipeline, pinpointing specific challenges that must be addressed to develop a robust solution for handling complex financial tasks.

cs.IR↗

arXiv2024

Soft Measures for Extracting Causal Collective Intelligence

Understanding and modeling collective intelligence is essential for addressing complex social systems. Directed graphs called fuzzy cognitive maps (FCMs) offer a powerful tool for encoding causal mental models, but extracting high-integrity FCMs from text is challenging. This study presents an approach using large language models (LLMs) to automate FCM extraction. We introduce novel graph-based similarity measures and evaluate them by correlating their outputs with human judgments through the Elo rating system. Results show positive correlations with human evaluations, but even the best-performing measure exhibits limitations in capturing FCM nuances. Fine-tuning LLMs improves performance, but existing measures still fall short. This study highlights the need for soft similarity measures tailored to FCM extraction, advancing collective intelligence modeling with NLP.

cs.CL↗

arXiv2024

MASSFormer: Mobility-Aware Spectrum Sensing using Transformer-Driven Tiered Structure

In this paper, we develop a novel mobility-aware transformer-driven tiered structure (MASSFormer) based cooperative spectrum sensing method that effectively models the spatio-temporal dynamics of user movements. Unlike existing methods, our method considers a dynamic scenario involving mobile primary users (PUs) and secondary users (SUs)and addresses the complexities introduced by user mobility. The transformer architecture utilizes an attention mechanism, enabling the proposed method to adeptly model the temporal dynamics of user mobility by effectively capturing long-range dependencies within the input data. The proposed method first computes tokens from the sequence of covariance matrices (CMs) for each SU and processes them in parallel using the SUtransformer network to learn the spatio-temporal features at SUlevel. Subsequently, the collaborative transformer network learns the group-level PU state from all SU-level feature representations. The attention-based sequence pooling method followed by the transformer encoder adjusts the contributions of all tokens. The main goal of predicting the PU states at each SU-level and group-level is to improve detection performance even more. We conducted a sufficient amount of simulations and compared the detection performance of different SS methods. The proposed method is tested under imperfect reporting channel scenarios to show robustness. The efficacy of our method is validated with the simulation results demonstrating its higher performance compared with existing methods in terms of detection probability, sensing error, and classification accuracy.

cs.IT↗