Hadi Mohammadi

Final Year PhD Candidate in Explainable NLP | Utrecht University

Seeking postdoc opportunities in NLP, Explainable AI, and Human-AI Collaboration

I'm an NLP Researcher

Hello! I'm Hadi

PhD Candidate in Explainable NLP for Social Sciences

Utrecht University | Faculty of Social and Behavioural Sciences

CV: [Download PDF]
Email: h.mohammadi@uu.nl
Location: Utrecht, The Netherlands
Expected Graduation: November 2025 (2.5 years)

University Profile: Official Page
ORCID: 0000-0003-0860-9200
Google Scholar: Publications
Research Groups: NLTP, HDS Lab

Research Focus

I am a final-year PhD candidate at Utrecht University specializing in Explainable Natural Language Processing (NLP) for Social Sciences. My research bridges the gap between advanced AI techniques and social science applications, focusing on developing transparent and interpretable NLP models that can be trusted and understood by domain experts.

With over 3 years of experience in the Netherlands and 6+ years in data science and machine learning, I have secured €38,400 in research funding and published in top venues including ACL, ECAI, and Applied Sciences. My work encompasses explainable AI, fairness in machine learning, human-AI collaboration, and the application of large language models (LLMs) to understand cultural and moral variations across societies.

Supervisory Team

I am fortunate to be supervised by an interdisciplinary team of experts:

• Dr. Ayoub Bagheri - Associate Professor, NLP and Machine Learning
• Dr. Anastasia Giachanou - Assistant Professor, Social Media Analysis and NLP
• Prof. Dr. Daniel Oberski - Professor, Data Science and Methodology

Recent News & Updates

📝 Paper Accepted at ECAI 2025

July 2025

Paper accepted at ECAI 2025 on cross-cultural morality understanding with Large Language Models.

💰 Secured €5K ADS Grant for LLM Research

June 2025

Awarded Applied Data Science Grant (€5,000) for the project "Rule Extraction from Human Evaluation Using LLMs and Reinforcement Learning" in collaboration with Dr. Anastasia Giachanou and Dr. Shihan Wang.

📝 Paper Accepted at ACL 2025

April 2025

Paper accepted at ACL 2025 (GeBNLP Workshop) on LLM reliability assessment and annotation reliability.

🚀 Received €9K CUCo Spark Grant

March 2025

Awarded Centre for Unusual Collaborations (CUCo) Spark Grant (€9,000) for "ReDOSE: Towards a more Circular Pharmaceutical Industry using AI" - an interdisciplinary collaboration across WUR, TU/e, and UMCU.

🎉 Selected for LERU Doctoral Summer School 2025

January 2025

Selected as the representative of the Faculty of Social and Behavioural Sciences, Utrecht University, for the prestigious LERU Doctoral Summer School on Artificial Intelligence in Copenhagen.

💶 Awarded €14.4K Enfield Grant

December 2024

Received European Lighthouse to Manifest Trustworthy and Green AI (Enfield) grant for research on "User Perspectives on Explainable AI".

🌐 Founded Young Scholar Networks for NLP@U

November 2024

Established a new research network uniting PhD candidates, postdocs, and junior researchers working on NLP and text mining across Utrecht University and UMC Utrecht.

🎤 Communications Chair at BNAIC/BeNeLearn 2024

November 2024

Served as Communications Chair for the Joint International Scientific Conferences on AI and Machine Learning at Utrecht University.

Facts

Years of Experience

Publications & Papers

Citations

Funding Secured (EUR)

Skills

Python 95%

PyTorch 85%

Hugging Face 90%

R 75%

SQL 80%

Git 85%

LaTeX 90%

SPSS 70%

Resume

Professional Experience

GenAI & LLMs Specialist

Jan 2023 - Present

AcademicTransfer, Utrecht, Netherlands

Developed CV Priority Sorter using Active Learning and LLMs, reducing HR hiring time by 20%
Built end-to-end generative AI pipelines for automatic insight extraction from CVs
Improved candidate-job alignment accuracy by 17% and halved manual effort

Researcher & NLP Developer

Feb 2024 - Mar 2024

Utrecht University School of Economics - FIRMBACKBONE Project

Developed fbb-sustainability-analysis-cli tool for sustainability content analysis
Created keyword extractor and index generator for sustainability scoring of websites

Senior Data Scientist in Customer Behavior

Dec 2021 - Dec 2022

SnowaTec (Innovation Center) - Entekhab Electronic, Tehran, Iran

Managed enterprise data warehouse with modern ETL tooling, improving data accessibility by 16%
Defined KPIs and customer satisfaction index that lifted satisfaction by 2%
Created interactive Power BI dashboards for data-driven decisions
Implemented ML-based customer segmentation, boosting marketing impact by 7.5%

Medior Data Scientist & Business Intelligence Analyst

Apr 2020 - Oct 2020

Bdood.bikes (Shared Bicycle System), Tehran, Iran

Implemented dynamic pricing and ML-based usage predictions, increasing revenue by 5%
Built dashboards with Power BI, Streamlit, and Dash Plotly, boosting engagement by 3%
Optimized fleet intelligence, cutting maintenance costs by 8% and relocation costs by 3%
Led user behavior analyses that improved customer retention by 4.5%

Junior Data Scientist

Jul 2019 - Apr 2020

Bdood.bikes (Shared Bicycle System), Tehran, Iran

Led predictive-maintenance analysis and battery-health algorithm development, reducing downtime by 3.8%
Applied GIS models to identify high-risk riders, enhancing safety by 3% and user experience by 5%
Provided marketing and business analytics insights contributing to 6% rise in revenue

Education

Ph.D. in Explainable Natural Language Processing

Feb 2023 - Nov 2025 (Expected)

Utrecht University, Faculty of Social and Behavioural Sciences

Department of Methodology & Statistics (Final year PhD candidate)
Member of NLTP (Natural Language and Text Processing) group and HDS (Human Data Science) Lab
Research focus: Explainable AI, Cultural Fairness in LLMs, Human-AI Collaboration
Secured €38,400 in research funding from multiple grants
Supervisors: Dr. Ayoub Bagheri, Dr. Anastasia Giachanou, Prof. Dr. Daniel Oberski

M.Sc. in Industrial Engineering—Macro Systems

Sep 2018 - Apr 2021

University of Tehran, Tehran, Iran

GPA: 18.96/20 (4.0/4.0) - Ranked 2nd among 50+ graduate students
Thesis: "Dynamic pricing with demand learning using reinforcement learning in non-stationary environment"

B.Sc. in Engineering

Sep 2011 - Jul 2016

Isfahan University of Technology, Golpayegan College of Engineering

Last 2 years GPA: 15.98/20 (3.35/4.0)

Professional Development

Generative Modeling Summer School

June 2024

Eindhoven University of Technology, Netherlands

Focus on Deep Generative Modeling techniques

Machine Learning Summer School

May - Jul 2023

University of Oxford, UK

Specialization in Finance & NLP/Health applications

Explainable AI Summer School

Aug 2022

TU Delft, Netherlands (Scholarship recipient)

Focus on post-hoc interpretability in machine learning

Executive Master in Finance (EMFin)

Nov 2021 - Nov 2022

Sharif University of Technology, Iran

One-year comprehensive finance program

Publications

My research papers on explainable AI, human-AI collaboration, and cultural fairness in LLMs

Explainability in Practice: A Survey of Explainable NLP

Hadi Mohammadi, Ayoub Bagheri, Anastasia Giachanou, Daniel L Oberski

View Details ArXiv

A Transparent Pipeline for Identifying Sexism in Social Media

Hadi Mohammadi, Anastasia Giachanou, Ayoub Bagheri

View Details Journal Code

Explainability-Based Token Replacement on LLM-Generated Text

Hadi Mohammadi, Anastasia Giachanou, Daniel Oberski, Ayoub Bagheri

View Details ArXiv Code

Assessing the Reliability of LLMs Annotations

Hadi Mohammadi, Tina Shahedi, Pablo Mosteiro Romero, Massimo Poesio, Ayoub Bagheri, Anastasia Giachanou

View Details ArXiv

Exploring Cultural Variations in Moral Judgments with LLMs

Hadi Mohammadi, Evi Papadopoulou, Mijntje Meijer, Ayoub Bagheri

View Details ArXiv Code

View All Publications

Research Interests

Explainable AI & Interpretability

Developing transparent and interpretable NLP models that provide human-understandable explanations. My work focuses on post-hoc interpretability methods, token-level explanations, and making AI systems more trustworthy for domain experts in social sciences.

Human-AI Collaboration

Investigating how humans and AI systems can work together effectively. This includes studying human rationalizations, improving AI-generated explanations to match human expectations, and developing frameworks for meaningful human-AI interaction.

Cultural Fairness in LLMs

Exploring how Large Language Models understand and represent cultural variations in moral judgments and social norms. My research aims to make AI systems more culturally aware and fair across different populations and contexts.

AI Safety & Reliability

Assessing the reliability of AI-generated content and annotations, especially in sensitive domains like hate speech and sexism detection. Developing methods to evaluate when we can trust LLM predictions and explanations.

Reinforcement Learning for NLP

Applying reinforcement learning techniques to improve NLP models, including rule extraction from human evaluations and dynamic adaptation of models based on user feedback and interaction patterns.

NLP for Social Sciences

Bridging computational methods with social science research questions. This includes analyzing social media data, understanding online discourse, and developing tools that help social scientists leverage NLP effectively.

Research Dissemination & Open Science

Committed to making research accessible and reproducible through open-source code repositories, detailed paper websites, and interactive demonstrations. I believe in transparent research practices that enable others to build upon and validate scientific findings, fostering collaborative advancement in NLP and AI research. View my publications →

Teaching & Supervision

Teaching Development

Pedagogical Training

2025 - Present

Utrecht University

Attended the Start to Teach course for novice teachers as the initial step toward the Basiskwalificatie Onderwijs (BKO), focusing on practical teaching skills, didactic training, and distance learning.

Student Supervision

Master's Thesis Co-Supervisor

2024 - 2025

Utrecht University - Applied Data Science Program

2024 Graduates: Meijer Meijer, Evi Papadopoulou, Lourenço Santos Moitinho de Almeida
2025 Current: Hein Brouwer, Tamás Kozák, Mohamad Jouhar
Co-supervised with Dr. Ayoub Bagheri and Dr. Anastasia Giachanou
Topics: Explainable AI, Cultural Fairness in LLMs, Human-AI Collaboration