Publications

Visit my Google Scholar profile for the most up-to-date list.

2026

Learning in Blocks: A Multi Agent Debate Assisted Personalized Adaptive Learning Framework for Language Learning

Scaria, N., Kennedy, S.J.J. and Subramani, D.

AIED 2026, pp. 399–413 Oral

Paper Code

Learning in Blocks: A Skill-Driven Framework for Assessment-Centered Agentic AI in Education

Scaria, N., Kennedy, S.J.J. and Subramani, D.

IRAISE 2026 (PMLR 339), pp. 101–106 Oral

Paper

HeteroForge: Heterogeneous Multi-Agent Debate for Curriculum-Aligned STEM Exercise Generation

Scaria, N., Kennedy, S.J.J. and Subramani, D.

IRAISE 2026 (PMLR 339), pp. 211–216 Poster

Paper

2025

Sensitivity of Small Language Models to Fine-tuning Data Contamination

Scaria, N., Kennedy, S.J.J. and Subramani, D.

arXiv:2511.06763

Paper Code

Harnessing Structured Knowledge: A Concept Map-Based Approach for High-Quality Multiple Choice Question Generation with Effective Distractors

Scaria, N., Kennedy, S.J.J., Seth, D., Thakur, A. and Subramani, D.

ECAI 2025, pp. 4089–4096 Oral

Paper Code

Dissecting Physics Reasoning in Small Language Models: A Multi-Dimensional Analysis from an Educational Perspective

Scaria, N., Kennedy, S.J.J., Agarwal, K., Seth, D. and Subramani, D.

arXiv:2505.20707

Paper

EvalYaks: Instruction Tuning Datasets and LoRA Fine-tuned Models for Automated Scoring of CEFR B2 Speaking Assessment Transcripts

Scaria, N., Kennedy, S.J.J., Latinovich, T. and Subramani, D.

Computers and Education: Artificial Intelligence, 100539

Paper Code

2024

Automated Educational Question Generation at Different Bloom's Skill Levels Using Large Language Models: Strategies and Evaluation

Scaria, N., Dharani Chenna, S. and Subramani, D.

AIED 2024, pp. 165–179 Oral

Paper Code

How Good are Modern LLMs in Generating Relevant and High-Quality Questions at Different Bloom's Skill Levels for Indian High School Social Science Curriculum?

Scaria, N., Chenna, S. and Subramani, D.

BEA 2024, pp. 1–10 Poster

Paper Code