Nitesh V. Chawla
YOU?
Author Swipe
View article: CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain?
CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain? Open
We present CrochetBench, a benchmark for evaluating the ability of multimodal large language models to perform fine-grained, low-level procedural reasoning in the domain of crochet. Unlike prior benchmarks that focus on high-level descript…
View article: Think it Image by Image: Multi-Image Moral Reasoning of Large Vision-Language Models
Think it Image by Image: Multi-Image Moral Reasoning of Large Vision-Language Models Open
View article: Proto-Yield: An Uncertainty-Aware Prototype Network for Yield Prediction in Real-world Chemical Reactions
Proto-Yield: An Uncertainty-Aware Prototype Network for Yield Prediction in Real-world Chemical Reactions Open
View article: SPECTRA: Spectral Target-Aware Graph Augmentation for Imbalanced Molecular Property Regression
SPECTRA: Spectral Target-Aware Graph Augmentation for Imbalanced Molecular Property Regression Open
In molecular property prediction, the most valuable compounds (e.g., high potency) often occupy sparse regions of the target space. Standard Graph Neural Networks (GNNs) commonly optimize for the average error, underperforming on these unc…
View article: Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks
Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks Open
Large language model evaluation requires thousands of benchmark items, making evaluations expensive and slow. Existing methods compute average accuracy across fixed item sets, treating all items equally despite varying quality and informat…
View article: LLMs4All: A Review of Large Language Models Across Academic Disciplines
LLMs4All: A Review of Large Language Models Across Academic Disciplines Open
Cutting-edge Artificial Intelligence (AI) techniques keep reshaping our view of the world. For example, Large Language Models (LLMs) based applications such as ChatGPT have shown the capability of generating human-like conversation on exte…
View article: Explanation Difference: Bridging Procedural and Distributional Fairness
Explanation Difference: Bridging Procedural and Distributional Fairness Open
Fairness in Machine Learning (Fair ML) is often presented as a trade-off between predictive performance and equality of predicted values. This view of fairness, commonly referred to as distributional fairness, fails to consider how a model…
View article: KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance
KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance Open
We present Knowledge Extraction on OMIn (KEO), a domain-specific knowledge extraction and reasoning framework with large language models (LLMs) in safety-critical contexts. Using the Operations and Maintenance Intelligence (OMIn) dataset, …
View article: The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models Open
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key method for improving Large Language Models' reasoning capabilities, yet recent evidence suggests it may paradoxically shrink the reasoning boundary rather than expa…
View article: LLMs4All: A Review of Large Language Models Across Academic Disciplines
LLMs4All: A Review of Large Language Models Across Academic Disciplines Open
Cutting-edge Artificial Intelligence (AI) techniques keep reshaping our view of the world. For example, Large Language Models (LLMs) based applications such as ChatGPT have shown the capability of generating human-like conversation on exte…
View article: ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions
ChemOrch: Empowering LLMs with Chemical Intelligence via Synthetic Instructions Open
Empowering large language models (LLMs) with chemical intelligence remains a challenge due to the scarcity of high-quality, domain-specific instruction-response datasets and the misalignment of existing synthetic data generation pipelines …
View article: Exploring Conversational Design Choices in LLMs for Pedagogical Purposes: Socratic and Narrative Approaches for Improving Instructor's Teaching Practice
Exploring Conversational Design Choices in LLMs for Pedagogical Purposes: Socratic and Narrative Approaches for Improving Instructor's Teaching Practice Open
Large language models (LLMs) typically generate direct answers, yet they are increasingly used as learning tools. Studying instructors' usage is critical, given their role in teaching and guiding AI adoption in education. We designed and e…
View article: AI Academy: Building Generative AI Literacy in Higher Ed Instructors
AI Academy: Building Generative AI Literacy in Higher Ed Instructors Open
Generative AI is reshaping higher education, yet research has focused largely on students, while instructors remain understudied despite their central role in mediating adoption and modeling responsible use. We present the \textit{AI Acade…
View article: National Running Club Database: Assessing Collegiate Club Athletes' Cross Country Race Results
National Running Club Database: Assessing Collegiate Club Athletes' Cross Country Race Results Open
The National Running Club Database (NRCD) aggregates 15,397 race results of 5,585 athletes from the 2023 and 2024 cross country seasons. This paper introduces the NRCD dataset, which provides insights into individual athlete progressions, …
View article: Combating Homelessness Stigma with LLMs: A New Multi-Modal Dataset for Bias Detection
Combating Homelessness Stigma with LLMs: A New Multi-Modal Dataset for Bias Detection Open
Homelessness is a persistent social challenge, impacting millions worldwide. Over 770,000 people experienced homelessness in the U.S. in 2024. Social stigmatization is a significant barrier to alleviation, shifting public perception, and i…
View article: 8th Workshop on Machine Learning in Finance
8th Workshop on Machine Learning in Finance Open
View article: Graph Foundation Models: Challenges, Methods, and Open Questions
Graph Foundation Models: Challenges, Methods, and Open Questions Open
View article: Large Language Models as Innovators: A Framework to Leverage Latent Space Exploration for Novelty Discovery
Large Language Models as Innovators: A Framework to Leverage Latent Space Exploration for Novelty Discovery Open
Innovative idea generation remains a core challenge in AI, as large language models (LLMs) often struggle to produce outputs that are both novel and relevant. Despite their fluency, LLMs tend to replicate patterns seen during training, lim…
View article: Spectral Manifold Harmonization for Graph Imbalanced Regression
Spectral Manifold Harmonization for Graph Imbalanced Regression Open
Graph-structured data is ubiquitous in scientific domains, where models often face imbalanced learning settings. In imbalanced regression, domain preferences focus on specific target value ranges that represent the most scientifically valu…
View article: Class-aware contrastive optimization for imbalanced text classification
Class-aware contrastive optimization for imbalanced text classification Open
The unique characteristics of text data make classification tasks a complex problem. Advances in unsupervised and semi-supervised learning and autoencoder architectures addressed several challenges. However, they still struggle with imbala…
View article: Context Attribution with Multi-Armed Bandit Optimization
Context Attribution with Multi-Armed Bandit Optimization Open
Understanding which parts of the retrieved context contribute to a large language model's generated answer is essential for building interpretable and trustworthy generative QA systems. We propose a novel framework that formulates context …
View article: On The Design Choices of Next Level LLMs
On The Design Choices of Next Level LLMs Open
View article: Differentially-private data synthetisation for efficient re-identification risk control
Differentially-private data synthetisation for efficient re-identification risk control Open
Protecting user data privacy can be achieved via many methods, from statistical transformations to generative models. However, they all have critical drawbacks. For example, creating a transformed data set using traditional techniques is h…
View article: ChemHGNN: A Hierarchical Hypergraph Neural Network for Reaction Virtual Screening and Discovery
ChemHGNN: A Hierarchical Hypergraph Neural Network for Reaction Virtual Screening and Discovery Open
Reaction virtual screening and discovery are fundamental challenges in chemistry and materials science, where traditional graph neural networks (GNNs) struggle to model multi-reactant interactions. In this work, we propose ChemHGNN, a hype…
View article: Graph Foundation Models: A Comprehensive Survey
Graph Foundation Models: A Comprehensive Survey Open
Graph-structured data pervades domains such as social networks, biological systems, knowledge graphs, and recommender systems. While foundation models have transformed natural language processing, vision, and multimodal learning through la…
View article: Intersectional Divergence: Measuring Fairness in Regression
Intersectional Divergence: Measuring Fairness in Regression Open
Fairness in machine learning research is commonly framed in the context of classification tasks, leaving critical gaps in regression. In this paper, we propose a novel approach to measure intersectional fairness in regression tasks, going …
View article: MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation
MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation Open
View article: Social and economic predictors of under-five stunting in Mexico: a comprehensive approach through the XGB model
Social and economic predictors of under-five stunting in Mexico: a comprehensive approach through the XGB model Open
social and economic deprivation, stunting, children, machine learning, XGB model, Mexico.
View article: Rethinking Evaluation in Compound Potency Prediction
Rethinking Evaluation in Compound Potency Prediction Open
Regression tasks are essential in many fields, including chemistry, where property prediction models are used to prioritize chemical compounds for experimental testing. In this context, it is common to maximize properties, such as potency,…
View article: Ventana a la Verdad (Window to the Truth): A Chatbot Application for Navigating The Colombian Truth Commission's Archives
Ventana a la Verdad (Window to the Truth): A Chatbot Application for Navigating The Colombian Truth Commission's Archives Open