Publications

Same Chart, Different Story: Bias in Vision-Language Chart Interpretation

Mizanur Rahman, Huan Wu, Arash Asgari, Enamul Hoque, Laleh Seyyed-Kalantari

EMNLP 2026 (Long Paper)

[ paper]

Algorithms Trained on Normal Chest X-rays Can Predict Health Insurance Types

Chi-Yu Chen, Rawan Abulibdeh, Arash Asgari, Sebastián Andrés Cajas Ordóñez, Leo Anthony Celi, Deirdre Goode, Hassan Hamidi, Ned McCague, Laleh Seyyed-Kalantari, Thomas Sounack, Po-Chih Kuo

Proceedings of the 9th International Conference on Medical Imaging with Deep Learning (MIDL), PMLR 315

[ paper] [preprint]

ZIP: Quantifying Which Words Matter in Zero-Shot Instructional Prompts

Nikta Gohari Sadr, Sangmitra Madhusudan, Arash Asgari, Hassan Sajjad, Laleh Seyyed-Kalantari, Ali Emami

Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)

[ paper]

Quantifying Metric and Model Agreement in Bias Evaluation of Large Language Models

Arash Asgari, Huan Wu, Amirreza Naziri, Mojtaba Kolahdouzi, Laleh Seyyed-Kalantari

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

[ paper] [ code]

MAM: Multinomial Attention Masking for Foundation Models on Sparse Single-Cell RNA-seq Data

Amirreza Naziri, Arash Asgari, Aijun An, Eleftherios Sachlos, Laleh Seyyed-Kalantari

Proceedings of the 7th Conference on Health, Inference, and Learning (CHIL), PMLR 333

[ paper]

Responsible Foundation Models for Healthcare: Risks, Opportunities, and Pathways to Responsibility

Laleh Seyyed-Kalantari, Mojtaba Kolahdouzi, Arash Asgari, Hassan Hamidi, Amirreza Naziri, Artur Parkhimchyk, Seyyed Matin Tavakoli Afshari, Huan Wu, Salamata Konate, Shahram Mohanna

AI for a Just World: Power, Liberation, and the People Left Behind (Chapter 6), Chapman & Hall/CRC

[ paper]

Improving Classification of Cell Types in Acute Myeloid Leukemia with Self-guided Masking Technique

Amirreza Naziri, Arash Asgari, Eleftherios Sachlos, Aijun An, Laleh Seyyed-Kalantari

NeurIPS 2025 Workshop: AI Virtual Cells and Instruments: A New Era in Drug Discovery and Development

[ paper]

MedPerturbing LLMs: A Comparative Study of Toxicity, Prompt Tuning, and Jailbreaks in Medical QA

Arash Asgari, Amirreza Naziri, Laleh Seyyed-Kalantari

Proceedings of the AAAI Symposium Series

[ paper]

From Bias to Breakdown: Benchmarking Failure Mode Analysis of Single-cell RNA Sequencing Foundation Models in Acute Myeloid Leukemia

Amirreza Naziri, Arash Asgari, Aijun An, Eleftherios Sachlos, Laleh Seyyed-Kalantari

Proceedings of the AAAI Symposium Series

[ paper]

Predicting the understandability of computational notebooks through code metrics analysis

Mojtaba Mostafavi Ghahfarokhi, Alireza Asadi, Arash Asgari, Bardia Mohammadi, Abbas Heydarnoori

Empirical Software Engineering

[ paper] [preprint]

DistilKaggle: a distilled dataset of Kaggle Jupyter notebooks

Mojtaba Mostafavi Ghahfarokhi, Arash Asgari, Mohammad Abolnejadian, Abbas Heydarnoori

Proceedings of the 21st International Conference on Mining Software Repositories

[ paper] [ code]