Posts by Collection

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

DistilKaggle: a distilled dataset of Kaggle Jupyter notebooks

Published in Proceedings of the 21st International Conference on Mining Software Repositories, 2024

DistilKaggle introduces a rigorously curated dataset of Kaggle Jupyter notebooks designed to support empirical studies and machine learning research.

Recommended citation: Mostafavi Ghahfarokhi, M., Asgari, A., Abolnejadian, M., & Heydarnoori, A. (2024). "DistilKaggle: a distilled dataset of Kaggle Jupyter notebooks." Proceedings of the 21st International Conference on Mining Software Repositories, 647-651.
Download Paper

Predicting the understandability of computational notebooks through code metrics analysis

Published in Empirical Software Engineering, 2025

This paper investigates how various code metrics can be utilized to evaluate and predict the understandability of computational notebooks.

Recommended citation: Ghahfarokhi, M. M., Asadi, A., Asgari, A., Mohammadi, B., & Heydarnoori, A. (2025). "Predicting the understandability of computational notebooks through code metrics analysis." Empirical Software Engineering, 30, 98.
Download Paper

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

Published in Proceedings of the AAAI Symposium Series, 2025

This study provides a comprehensive benchmarking of failure modes in foundation models applied to single-cell RNA sequencing data for Acute Myeloid Leukemia.

Recommended citation: Naziri, A., Asgari, A., An, A., Sachlos, E., & Seyyed-Kalantari, L. (2025). "From Bias to Breakdown: Benchmarking Failure Mode Analysis of Single-cell RNA Sequencing Foundation Models in Acute Myeloid Leukemia." Proceedings of the AAAI Symposium Series, 7(1), 553-557.
Download Paper

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

Published in Proceedings of the AAAI Symposium Series, 2025

This comparative study evaluates the robustness and safety of Large Language Models (LLMs) in the context of medical question-answering.

Recommended citation: Asgari, A., Naziri, A., & Seyyed-Kalantari, L. (2025). "MedPerturbing LLMs: A Comparative Study of Toxicity, Prompt Tuning, and Jailbreaks in Medical QA." Proceedings of the AAAI Symposium Series, 7(1), 438-447.
Download Paper

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

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

This research presents a novel computational approach utilizing self-guided masking techniques to enhance the classification of cell types in Acute Myeloid Leukemia.

Recommended citation: Naziri, A., Asgari, A., Sachlos, E., An, A., & Seyyed-Kalantari, L. (2025). Improving Classification of Cell Types in Acute Myeloid Leukemia with Self-guided Masking Technique. NeurIPS 2025 Workshop: AI Virtual Cells and Instruments: A New Era in Drug Discovery and Development.
Download Paper

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

Published in AI for a Just World: Power, Liberation, and the People Left Behind (Chapter 6), Chapman & Hall/CRC, 2026

A book chapter on the risks, opportunities, and responsible use of foundation models in healthcare.

Recommended citation: Seyyed-Kalantari, L., Kolahdouzi, M., Asgari, A., Hamidi, H., Naziri, A., Parkhimchyk, A., Tavakoli Afshari, S. M., Wu, H., Konate, S., & Mohanna, S. (2026). Responsible Foundation Models for Healthcare: Risks, Opportunities, and Pathways to Responsibility. In AI for a Just World: Power, Liberation, and the People Left Behind, Chapter 6, 72–81. Chapman & Hall/CRC.
Download Paper

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

Published in Proceedings of the 7th Conference on Health, Inference, and Learning (CHIL), PMLR 333, 2026

MAM learns which gene positions to mask when pretraining foundation models on sparse single-cell RNA-seq data.

Recommended citation: Naziri, A., Asgari, A., An, A., Sachlos, E., & Seyyed-Kalantari, L. (2026). MAM: Multinomial Attention Masking for Foundation Models on Sparse Single-Cell RNA-seq Data. Proceedings of the 7th Conference on Health, Inference, and Learning, PMLR 333, 295–311.
Download Paper

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

Published in Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

This paper presents a comprehensive study quantifying the agreement across various bias evaluation metrics and Large Language Models (LLMs), aiming to provide a more robust understanding of fairness assessments in natural language processing.

Recommended citation: Asgari, A., Wu, H., Naziri, A., Kolahdouzi, M., & Seyyed-Kalantari, L. (2026). "Quantifying Metric and Model Agreement in Bias Evaluation of Large Language Models." Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 16868–16933.
Download Paper

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

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

ZIP measures the importance of individual words in zero-shot instructional prompts through controlled perturbations.

Recommended citation: Gohari Sadr, N., Madhusudan, S., Asgari, A., Sajjad, H., Seyyed-Kalantari, L., & Emami, A. (2026). ZIP: Quantifying Which Words Matter in Zero-Shot Instructional Prompts. Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026), 428–453.
Download Paper

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

Published in Proceedings of the 9th International Conference on Medical Imaging with Deep Learning (MIDL), PMLR 315, 2026

This research demonstrates that machine learning algorithms trained solely on normal chest X-rays can inadvertently learn to predict a patient`s health insurance type.

Recommended citation: Chen, C.-Y., Abulibdeh, R., Asgari, A., Ordóñez, S. A. C., Celi, L. A., Goode, D., Hamidi, H., McCague, N., Seyyed-Kalantari, L., Sounack, T., & Kuo, P.-C. (2026). Algorithms Trained on Normal Chest X-rays Can Predict Health Insurance Types. Proceedings of the 9th International Conference on Medical Imaging with Deep Learning, PMLR 315, 4166–4181.
Download Paper

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

Published in EMNLP 2026 (Long Paper), 2026

ChartBias evaluates bias in vision-language chart interpretation through narrative shift, group hallucination, and preference polarity.

Recommended citation: Rahman, M., Wu, H., Asgari, A., Hoque, E., & Seyyed-Kalantari, L. (2026). Same Chart, Different Story: Bias in Vision-Language Chart Interpretation. EMNLP 2026.
Download Paper

Talk 1 on Relevant Topic in Your Field

Published: March 01, 2012

This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!

Tutorial 1 on Relevant Topic in Your Field

Published: March 01, 2013

More information here

Talk 2 on Relevant Topic in Your Field

Published: February 01, 2014

More information here

Conference Proceeding talk 3 on Relevant Topic in Your Field

Published: March 01, 2014

This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.