arXiv subjects

Anurag Sharma

Publications and source records attributed to Anurag Sharma.

12 recordsLinked to original sources

arXiv2026

Exploring ESC Winners with Nested Diagrams

We present ConceptFlow, a scikit-learn-compatible Python library for Formal Concept Analysis that constructs and renders nested line diagrams from many-valued formal contexts. Given a many-valued context and a partition of its attributes into conceptual scales, ConceptFlow performs conceptual scaling, computes the factor lattices, identifies filled nodes of the corresponding subdirect product, and produces an interactive visualization. We apply ConceptFlow to the winners of the Eurovision Song Contest from 1975 to 2025, exploring relationships between voting patterns and musical characteristics. Voting support is captured by an outer scale spanning regional, cultural, historical, and political dimensions, while an inner scale captures musical characteristics via tempo and key. The resulting nested line diagram reveals implications across both scales, exposing dependencies between how winning entries were voted for and the musical properties they share.

cs.AI↗

arXiv2026

PROSLEX: A Novel Dataset for Expert-Annotated Legal Statute Prediction for Indian Judiciary

Legal Statute Prediction (LSP) involves automatically identifying relevant legal statutes given factual descriptions in legal documents, typically framed as a multi-label classification task within natural language processing and information retrieval research. While recent advances have begun incorporating Large Language Models (LLMs) for statute prediction, current approaches primarily focus on accuracy metrics without addressing the critical need for legal reasoning, a fundamental requirement in judicial contexts where decisions must be explainable and justifiable. To address this research gap, we present PROSLEX (PRediction Of Statutes and LEgal eXplanation), a comprehensive dataset comprising 1,623 expert-annotated legal documents from the Indian context. Each document is paired with statute predictions and detailed explanations, totaling 7,450 explanations, capturing the underlying legal reasoning. Using this dataset, we systematically evaluate various prompting strategies, including zero-shot, few-shot, chain-of-thought, and tree-of-thoughts approaches, to generate both statute predictions and their corresponding legal rationales. Our evaluation framework measures not only predictive performance but also the coherence and legal validity of generated explanations, positioning PROSLEX as a benchmark for developing explainable AI systems that can support legal practitioners while advancing research in interpretable legal NLP. To ensure reproducibility, we have made our PROSLEX dataset and model code available on GitHub: https://github.com/subinay494/Legal_Statute_Prediction_Explanation.

cs.AI↗

arXiv2026

REMEDI: A Benchmark for Retention and Unlearning Evaluation in Multi-label Clinical Disease Inference

Language models trained for clinical disease inference are trained on patient data, which may include sensitive and private information, and data owners may request the removal of their data from a trained model due to privacy or copyright concerns. However, exactly unlearning patient-specific data is intractable, and retraining with minor data removal is resource-intensive. While there exists several machine unlearning methods that can be used, their utility is generally restricted to non-medical domains. Moreover, the existing benchmarks for evaluating such unlearning methods primarily utilize synthetically curated datasets, which are not truly representative of real-world systems. Hence, the effectiveness of these unlearning methods in the medical domain is largely unclear. To this end, we introduce REMEDI, an extensive benchmark for machine unlearning tailored to multi-label and multiclass clinical disease inference, where label correlations, longitudinal structure, and safety constraints make unlearning particularly challenging. Unlike the existing benchmarks, REMEDI considers: (1) a relevant application domain (medical), (2) comprehensive unlearning setups involving diverse sets of forget instances, (3) challenging unlearning scenarios including multi-label and multi-class classification tasks, and (4) evaluation metrics involving performance both in terms of utility and extent of unlearning achieved. REMEDI is developed using the MIMIC-III clinical database that contains comprehensive clinical data of patients. Experiments with existing unlearning methods indicate that there exists a trade-off between utility and unlearning performance. They are also largely unsuited to multi-label classification tasks. To facilitate reproducibility, we make our benchmark publicly available.

cs.LG↗

arXiv2026

Minimalistic Terminal Editor for Julia Programming -- MinTEJ: A Friendly Approach for a Scientific Programmer

Developers rely on lightweight, terminal-centric workflows for rapid code iteration. However, within a unified environment for Julia programming language, existing tools provide limited support for integrated workflow such as editing, execution, file management, and debugging. As a result, developers frequently incur context-switching overhead and fragmented tool interactions. Therefore, the proposed work predominantly focuses on the minimalistic approach for developing native terminal editor for Julia programming language. This paper introduces MinTEJ, a terminal-based editor built in Julia, and proposes a Sequential Modal Interaction Architecture (SMIA) that unifies file management, code editing, execution, and debugging through a command-oriented workflow. The presented work formalizes model interaction and reduces cognitive load & errors while transitioning among different modes. In SMIA, buffer is the central data structure that persists across all modes. Each mode interprets and manipulates the buffer according to mode-specific rules. The central controller mediates access to the buffer and enforces sequential transitions between modes. To evaluate the approach, the performance benchmarking of MinTEJ is compared against existing tools i.e., VS code and Notepad++. The effectiveness of the proposed MinTEJ is evaluated based on memory consumption and CPU utilization demonstrating that it has less resource overhead. Findings suggest that integrated terminal-based editor environment is a practical lightweight software tool enabling efficient iterative development.

cs.SE↗

arXiv2026

LaMSUM: Amplifying Voices Against Harassment through LLM Guided Extractive Summarization of User Incident Reports

Citizen reporting platforms help the public and authorities stay informed about sexual harassment incidents. However, the high volume of data shared on these platforms makes reviewing each individual case challenging. Therefore, a summarization algorithm capable of processing and understanding various code-mixed languages is essential. In recent years, Large Language Models (LLMs) have shown exceptional performance in NLP tasks, including summarization. LLMs inherently produce abstractive summaries by paraphrasing the original text, while the generation of extractive summaries - selecting specific subsets from the original text - through LLMs remains largely unexplored. Moreover, LLMs have a limited context window size, restricting the amount of data that can be processed at once. We tackle these challenges by introducing LaMSUM, a novel multi-level framework combining summarization with different voting methods to generate extractive summaries for large collections of incident reports using LLMs. Extensive evaluation using four popular LLMs (Llama, Mistral, Claude and GPT-4o) demonstrates that LaMSUM outperforms state-of-the-art extractive summarization methods. Overall, this work represents one of the first attempts to achieve extractive summarization through LLMs, and is likely to support stakeholders by offering a comprehensive overview and enabling them to develop effective policies to minimize incidents of unwarranted harassment.

cs.CL↗

arXiv2026

FLNet: Flood-Induced Agriculture Damage Assessment using Super Resolution of Satellite Images

Distributing government relief efforts after a flood is challenging. In India, the crops are widely affected by floods; therefore, making rapid and accurate crop damage assessment is crucial for effective post-disaster agricultural management. Traditional manual surveys are slow and biased, while current satellite-based methods face challenges like cloud cover and low spatial resolution. Therefore, to bridge this gap, this paper introduced FLNet, a novel deep learning based architecture that used super-resolution to enhance the 10 m spatial resolution of Sentinel-2 satellite images into 3 m resolution before classifying damage. We tested our model on the Bihar Flood Impacted Croplands Dataset (BFCD-22), and the results showed an improved critical "Full Damage" F1-score from 0.83 to 0.89, nearly matching the 0.89 score of commercial high-resolution imagery. This work presented a cost-effective and scalable solution, paving the way for a nationwide shift from manual to automated, high-fidelity damage assessment.

cs.CV↗

arXiv2025

In silico Deep Learning Protocols for Label-Free Super-Resolution Microscopy: A Comparative Study of Network Architectures and SNR Dependence

The field of optical microscopy spans across numerous industries and research domains, ranging from education to healthcare, quality inspection and analysis. Nonetheless, a key limitation often cited by optical microscopists refers to the limit of its lateral resolution (typically defined as ~200nm), with potential circumventions involving either costly external modules (e.g. confocal scan heads, etc) and/or specialized techniques [e.g. super-resolution (SR) fluorescent microscopy]. Addressing these challenges in a normal (non-specialist) context thus remains an aspect outside the scope of most microscope users & facilities. This study thus seeks to evaluate an alternative & economical approach to achieving SR optical microscopy, involving non-fluorescent phase-modulated microscopical modalities such as Zernike phase contrast (PCM) and differential interference contrast (DIC) microscopy. Two in silico deep neural network (DNN) architectures which we developed previously (termed O-Net and Theta-Net) are assessed on their abilities to resolve a custom-fabricated test target containing nanoscale features calibrated via atomic force microscopy (AFM). The results of our study demonstrate that although both O-Net and Theta-Net seemingly performed well when super-resolving these images, they were complementary (rather than competing) approaches to be considered for image SR, particularly under different image signal-to-noise ratios (SNRs). High image SNRs favoured the application of O-Net models, while low SNRs inclined preferentially towards Theta-Net models. These findings demonstrate the importance of model architectures (in conjunction with the source image SNR) on model performance and the SR quality of the generated images where DNN models are utilized for non-fluorescent optical nanoscopy, even where the same training dataset & number of epochs are being used.

cs.CV↗

arXiv2024

Legal Judgment Reimagined: PredEx and the Rise of Intelligent AI Interpretation in Indian Courts

In the era of Large Language Models (LLMs), predicting judicial outcomes poses significant challenges due to the complexity of legal proceedings and the scarcity of expert-annotated datasets. Addressing this, we introduce \textbf{Pred}iction with \textbf{Ex}planation (\texttt{PredEx}), the largest expert-annotated dataset for legal judgment prediction and explanation in the Indian context, featuring over 15,000 annotations. This groundbreaking corpus significantly enhances the training and evaluation of AI models in legal analysis, with innovations including the application of instruction tuning to LLMs. This method has markedly improved the predictive accuracy and explanatory depth of these models for legal judgments. We employed various transformer-based models, tailored for both general and Indian legal contexts. Through rigorous lexical, semantic, and expert assessments, our models effectively leverage \texttt{PredEx} to provide precise predictions and meaningful explanations, establishing it as a valuable benchmark for both the legal profession and the NLP community.

cs.CL↗

arXiv2024

Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification

Employing Large Language Models (LLM) in various downstream applications such as classification is crucial, especially for smaller companies lacking the expertise and resources required for fine-tuning a model. Fairness in LLMs helps ensure inclusivity, equal representation based on factors such as race, gender and promotes responsible AI deployment. As the use of LLMs has become increasingly prevalent, it is essential to assess whether LLMs can generate fair outcomes when subjected to considerations of fairness. In this study, we introduce a framework outlining fairness regulations aligned with various fairness definitions, with each definition being modulated by varying degrees of abstraction. We explore the configuration for in-context learning and the procedure for selecting in-context demonstrations using RAG, while incorporating fairness rules into the process. Experiments conducted with different LLMs indicate that GPT-4 delivers superior results in terms of both accuracy and fairness compared to other models. This work is one of the early attempts to achieve fairness in prediction tasks by utilizing LLMs through in-context learning.

cs.CL↗

arXiv2023

Structural, vibrational and electronic properties of Nb substituted orthovanadates LaV$_{1-x}$Nb$_x$O$_4$

We investigate the structural, vibrational, morphological, and electronic properties of Nb substituted orthovanadate LaV$_{1-x}$Nb$_x$O$_4$ samples prepared by the solid-state reaction method. The x-ray diffraction (XRD) analysis reveals the presence of three crystal structures [monoclinic monazite ($m-m$) type for the $x=$ 0, two-phase equilibrium of monoclinic monazite ($m-m$) and tetragonal scheelite ($t-s$) type for the 0.2$\leq$$x$$\leq$0.8, and monoclinic fergusonite ($m-f$) type for the $x=$ 1 samples] with an increase in Nb$^{5+}$ concentration. The Raman spectroscopy and x-ray photoelectron spectroscopy (XPS) were employed to study the vibrational and electronic properties of all the samples, respectively. In order to choose an excitation wavelength that does not cause undesirable fluorescence and has observable intensities of all the vibrational modes, the Raman spectra are collected using 532 nm, 633 nm, and 785 nm laser lines. With increasing the Nb$^{5+}$ concentration, new Raman modes associated with Nb-bonds are clearly visible and the intensity of V-bonds assigned modes is decreasing. The XPS analysis shows the unchanged 3+ oxidation state of La ion where the intensity of the V 2$p$ core-level decreases while the Nb 3$d$ core-level increases with $x$. The equal spin-orbit energy splitting of the states is confirmed by the average energy difference (across La core-level spectra for all the samples) for state I as well as bonding and anti-bonding of state II. Interesting, the relative intensity of La 3$d$ state I and state II show systematic change with Nb doping altering the metal ligand overlap. We discuss and provide insight into the evolution of the structural, morphological, and chemical features with Nb substitution in LaV$_{1-x}$Nb$_x$O$_4$ samples.

cond-mat.mtrl-sci↗

arXiv2022

A Unified Framework for Optimization-Based Graph Coarsening

Graph coarsening is a widely used dimensionality reduction technique for approaching large-scale graph machine learning problems. Given a large graph, graph coarsening aims to learn a smaller-tractable graph while preserving the properties of the originally given graph. Graph data consist of node features and graph matrix (e.g., adjacency and Laplacian). The existing graph coarsening methods ignore the node features and rely solely on a graph matrix to simplify graphs. In this paper, we introduce a novel optimization-based framework for graph dimensionality reduction. The proposed framework lies in the unification of graph learning and dimensionality reduction. It takes both the graph matrix and the node features as the input and learns the coarsen graph matrix and the coarsen feature matrix jointly while ensuring desired properties. The proposed optimization formulation is a multi-block non-convex optimization problem, which is solved efficiently by leveraging block majorization-minimization, $\log$ determinant, Dirichlet energy, and regularization frameworks. The proposed algorithms are provably convergent and practically amenable to numerous tasks. It is also established that the learned coarsened graph is $ε\in(0,1)$ similar to the original graph. Extensive experiments elucidate the efficacy of the proposed framework for real-world applications.

stat.ML↗

arXiv2016

Low Cost Autonomous Navigation and Control of a Mechanically Balanced Bicycle with Dual Locomotion Mode

On the lines of the huge and varied efforts in the field of automation with respect to technology development and innovation of vehicles to make them run autonomously, this paper presents an innovation to a bicycle. A normal daily use bicycle was modified at low cost such that it runs autonomously, while maintaining its original form i.e. the manual drive. Hence, a bicycle which could be normally driven by any human and with a press of switch could run autonomously according to the needs of the user has been developed.

cs.RO↗