PhD Student in Computer Science @ Rutgers University β researching safe, fair, and explainable large language models.
π New Brunswick, NJ Β· βοΈ a.khorramrouz@rutgers.edu Β· π akhorramrouz.com Β· π Google Scholar
π Education
PhD, Computer Science
Rutgers University Β· New Brunswick, NJ Β· 2024 β Present
- Research Assistant advised by Prof. Sharon Levy
- CGPA: 4.0 / 4.0
M.Sc., Data Science
Rochester Institute of Technology Β· Rochester, NY Β· 2022 β 2024
- Fully funded M.Sc. awarded by Prof. Ashique KhudaBukhsh
- Research Assistant at Social Insight Lab
- CGPA: 4.0 / 4.0
π¬ Research Interests
- NLP & Large Language Models
- Responsible AI: Safety, Fairness & Bias Mitigation
- Explainable AI
- Computational Social Science for AI Evaluation
- Agentic AI & Multi-Agent Systems
π Publications & Preprints
Under Review
Moral Combat: Exploiting Moral Foundations Theory to Jailbreak LLMs
Adel Khorramrouz, Y. Wang, S. Levy
NAACL 2027 SubmittedWhere Guardrails Blur: Generating Domain-Specific Boundary Cases
Adel Khorramrouz, K. Foley, S. Hamidian
NAACL 2027 Submitted
2026
Characterizing Selective Refusal Bias in Large Language Models
Adel Khorramrouz, S. Levy
ACL 2026 Findings of the Association for Computational Linguistics Β· π PaperDetecting Subtle Biases: An Ethical Lens on Underexplored Areas in AI Language Models Biases
S. Bali, F. Farsi, M. Hosseini, Adel Khorramrouz, E. Asgari
EACL 2026 Proceedings of the European Chapter of the ACL Β· π€ Oral Presentation Β· π Paper
2024
A Survival Guide for Women in Iran: Harnessing LLMs and Participatory AI to Investigate Intimate Partner Physical Violence in Iran
Adel Khorramrouz, M. Fayazi, A. KhudaBukhsh
IJCAI 2024 Proceedings of the 33rd International Joint Conference on Artificial Intelligence (also accepted in Findings of EMNLP 2023) Β· π PaperDown the Toxicity Rabbit Hole: A Framework to Bias Audit Large Language Models with Key Emphasis on Racism, Antisemitism, and Misogyny
Adel Khorramrouz, A. Dutta, S. Dutta, A. KhudaBukhsh
IJCAI 2024 AI for Good Track Β· π° Featured in WIRED Β· π PaperNovax or Novak? Estimating Social Media Stance towards Celebrity Vaccine Hesitancy (Student Abstract)
H. Madhav, Adel Khorramrouz, A. KhudaBukhsh
AAAI 2024 Proceedings of the AAAI Conference on Artificial Intelligence Β· π Paper
2023
-
For Women, Life, Freedom: A Participatory AI-Based Social Web Analysis of a Watershed Moment in Iran's Gender Struggles
Adel Khorramrouz, S. Dutta, A. KhudaBukhsh
IJCAI 2023 AI for Good Track Β· π Link
2021 β 2022
Coronal Deformity Angular Ratio as a Predictive Factor for In-Brace Curve Correction and Long-Term Outcome of Brace Treatment in Adolescents with Idiopathic Scoliosis
T. Babaee, M. Kamyab, M. S. Ganjavian, N. Rouhani, Adel Khorramrouz, J. Jarvis
Spine Deformity 2022 Β· π PaperA Convolution Neural Network Approach to Predict Pes-Planus Using Plantar Pressure Mapping Images
Adel Khorramrouz, M. Ahmadi Bani, M. Lalenoor, M. Bagheri
IJHME 2021 Int. Journal of Health and Medical Engineering, Vol. 15, No. 12 Β· π PaperNeural Network and Support Vector Machine for Prediction of Foot Disorders Based on Foot Analysis
M. Ahmadi Bani, Adel Khorramrouz, M. Lalenoor, M. Bagheri
IJHME 2021 Int. Journal of Health and Medical Engineering, Vol. 15, No. 12 Β· π PaperDecision-Tree-Based Foot Disorders Classification Using Demographic Variable
Adel Khorramrouz, M. Ahmadi Bani, E. Noruzi
IJHME 2021 Int. Journal of Health and Medical Engineering, Vol. 15, No. 12 Β· π Paper
πΌ Work Experience
Machine Learning Engineer (Returning Intern) β Comcast
π May 2026 β Sep 2026
Content Discovery Team Β· Synthetic data generation for LLM guardrails Β· Manager: Sardar Hamidian
Machine Learning Research Intern β Comcast
π May 2025 β May 2026
Content Discovery Team Β· Guardrail development and recommendation-system safety Β· Mentor: Kevin Foley
Research Intern β BioInfo Lab
π Summer 2024
Protein Language Models Β· Fine-tuning with PEFT Β· LoRA Β· QLoRA Β· Mixture of Experts
Research Intern β Social Insight Lab
π Summer 2023
Multilingual LLMs Β· Instruction Tuning Β· Fairness Β· Safety & Guardrails
Data Scientist β Apply 4 Fund
π Summer 2022
Social Media Web Scraping Β· Web Application Development Β· Data Analytics
Founder β PolyEkip
π Jun 2019 β Mar 2020
Developed an AI-based friend-finding algorithm based on psychological personality assessment
π§ͺ Research Experience
- Research Assistant, Levy Research Group, Rutgers University β Supervisor: Dr. Sharon Levy Β· Sep 2024 β Present
- Research Assistant, Cui Research Group, Rochester Institute of Technology β Supervisor: Dr. F. Cui Β· May 2024 β Aug 2024
- Research Assistant, Social Insight Lab, Rochester Institute of Technology β Supervisor: Dr. Ashique KhudaBukhsh Β· Sep 2022 β May 2024
- Research Intern, Natural Language and Speech Processing Lab, Tehran, Iran β Supervisor: Dr. S. Seyedin Β· 2022
ποΈ Academic Service
- Reviewer β ACL, COLM, COLING
- Volunteer β ACL 2023
- Judge β Genius Olympiad, with participants representing 45+ countries
π° Media Coverage
- WIRED featured our research on bias auditing in large language models, emphasizing its socio-political implications.
- Montreal AI Ethics Institute highlighted our work on bias auditing of LLMs.
- RIT News featured our research findings on bias auditing in large language models.
π Honors & Awards
- 2022 Fully funded scholarship β $120,000 USD (2022 β 2024)
- 2017 Ranked 109th among 148K contenders (top 0.07%) in the national university entrance examination
- 2010 β 2017 Admitted to the National Organization for Development of Exceptional Talents
π¨βπ« Teaching Experience
- Fall 2025 Machine Learning Principles β Teaching Assistant Β· Prof. Sharon Levy
- Spring 2025 Natural Language Processing β Teaching Assistant Β· Prof. Sharon Levy
- Fall 2024 Introduction to Data Science β Teaching Assistant Β· Prof. Gunawardena
- Spring 2022 Computer Vision Project β Leading Teaching Assistant Β· Prof. S. Seyedin
- Spring 2022 Introduction to Artificial Intelligence β Leading Teaching Assistant Β· Prof. M. Ahmadi
- Spring 2022 Introduction to Computational Social Science β Workshop Lecturer
- Fall 2021 & Spring 2022 Machine Learning β Teaching Assistant Β· Prof. S. Seyedin
- Fall 2021 Statistical Learning Theory β Teaching Assistant Β· Prof. V. Pourahmadi
βΆοΈ Online Education (YouTube) β Machine Learning Concepts and Coding Series Β· Python and OOP Tutorial Series
π οΈ Skills
- Programming β Python (Advanced) Β· Java Β· C++ Β· MATLAB
- Machine Learning β PyTorch Β· TensorFlow Β· HuggingFace Transformers Β· Scikit-learn Β· Keras
- Data Processing β Pandas Β· NumPy Β· SciPy Β· BeautifulSoup
- NLP β Prompt Engineering Β· LLM Fine-tuning (LoRA, QLoRA, MoE) Β· Instruction Tuning Β· Multilingual NLP
- Generative AI β Large Language Models Β· Vision-Language Models
- LLM Guardrails & Safety β Content Moderation Β· Harmful Content Detection Β· Guardrail Implementation & Evaluation
- AI Ethics & Fairness β Bias Auditing Β· Ethical AI Frameworks Β· Trustworthy AI Evaluation
- Explainable AI β Model Interpretability Β· Feature Importance Analysis Β· Explanation Generation
- Soft Skills β Research Leadership Β· Problem Solving Β· Academic Writing Β· Public Speaking Β· Workshop Facilitation