PhD Candidate · Computer Science

Christabel Acquaye

University of Maryland, College Park
Advised by Prof. Rachel Rudinger · CLIP Lab

I am a fifth-year PhD student researching the development, fine-tuning, and evaluation of large language models to improve natural language understanding, with emphasis on commonsense reasoning, cultural alignment, question item generation and difficulty estimation, and fairness. My work spans cross-cultural benchmarking, LLM-based student simulation, and building trustworthy NLP systems that work equitably across diverse populations.

Email Scholar LinkedIn
College Park, MD · Open to relocation
Christabel Acquaye
Research

Research Interests

LLM Evaluation Post-Training & RLHF Personalization Commonsense Reasoning Cultural Alignment Educational NLP Fairness & Bias Question Answering Item Response Theory Multimodal AI Cross-Cultural Evaluation LLM Adaptation

Advised by Prof. Rachel Rudinger at University of Maryland, College Park · CLIP Lab

Updates

News

Oct 2026
Paper accepted to the 2nd Workshop on MUCG: Multimodal Large Language Models for Unified Comprehension and Generation: Scene-Graph Guided Conditioning for Text-to-Image Generation with Hirunima Jayasekara and Ashira Jayaweera.
Oct 2026
Paper accepted to the FLLM Main Track: From Transcripts to Insights: LLM-Assisted Topic Discovery in Customer Feedback Surveys.
July 2026
Paper presented at ACL 2026: Take Out Your Calculators: Estimating the Real Difficulty of Question Items with LLM Student Simulations and IRT.
July 2026
Paper accepted to ICPR 2026: All-in-One Conditioning for Text-to-Image Synthesis with Hirunima Jayasekara et al.
2025
Oral presentation at RTC Conference 2025: From Transcripts to Insights.
Jun 2025
Started NLP Research Internship at Vail Systems, Inc. in Chicago, IL.
Research Output

Publications

* denotes equal contribution

FLLM · Main Track · Accepted
From Transcripts to Insights: LLM-Assisted Topic Discovery in Customer Feedback Surveys
Christabel Acquaye, Jordan Hosier, Yu Zhou, Vijay K. Gurbani
Topic ModelingSentiment AnalysisRAGAgentic LLM
2nd Workshop on MUCG · Accepted
Scene-Graph Guided Conditioning for Text-to-Image Generation
Hirunima Jayasekara, Christabel Acquaye, Ashira Jayaweera
Text-to-ImageScene GraphsMultimodal
ACL 2026 · Published
Take Out Your Calculators: Estimating the Real Difficulty of Question Items with LLM Student Simulations and IRT
Christabel Acquaye, Yi Ting Huang, Marine Carpuat, Rachel Rudinger
[arXiv]
Educational NLPIRTLLM SimulationMath Assessment
ICPR 2026 · Accepted
All-in-One Conditioning for Text-to-Image Synthesis
Hirunima Jayasekara, Chuong Huynh, Yixuan Ren, Christabel Acquaye, Abhinav Shrivastava
[arXiv]
Text-to-ImageScene GraphsMultimodalDiffusion Models
NAACL 2025 · Published
My LLM Might Mimic AAE — But When Should It?
Sandra Camille Sandoval*, Christabel Acquaye*, Kwesi Adu Cobbina*, Mohammad Nayeem Teli, Hal Daumé III
Language FairnessAAEEthicsLLM
EMNLP 2024 · Published
Susu Box or Piggy Bank: Assessing Cultural Commonsense Knowledge between Ghana and the US
Christabel Acquaye, Haozhe An, Rachel Rudinger
[arXiv] [Dataset]
Cultural NLPCommonsenseBenchmarkGhana
ACL 2024 · Published
Do Large Language Models Discriminate in Hiring Decisions on the Basis of Race, Ethnicity, and Gender?
Haozhe An, Christabel Acquaye, Colin Wang, Zongxia Li, Rachel Rudinger
[arXiv]
FairnessHiring BiasLLM Evaluation
Harvard Dataverse 2022 · Dataset
KaraAgroAI Cocoa and Maize Dataset
Darlington Akogo, Christabel Acquaye, Emmanuel Amoako, Jerry Buaba, Issah Samori, et al.
[Dataset]
Cocoa: 1,518 downloads · Maize: 2,670 downloads
Agriculture AIComputer VisionOpen Data
Mentorship

Teaching

University of Maryland

Teaching Assistant Aug 2022 — Present
CMSC 470
Introduction to Natural Language Processing
Spring 2026
Instructor: Prof. Rachel Rudinger
CMSC 828J
Common-Sense Reasoning and Natural Language Understanding
Fall 2025 · Graduate Seminar
Instructor: Prof. Rachel Rudinger
CMSC 216
Introduction to Computer Systems
Summer 2023, Summer 2024
Course page ↗
CMSC 320
Introduction to Data Science
University of Maryland
Course page ↗
CMSC 131 / 132
Object-Oriented Programming I and II
University of Maryland
Course page ↗

Academic City University College

Faculty Assistant May 2021 — Aug 2022
Emerging Technologies, Matlab for Algebra & Python Programming
Accra, Ghana

Kwame Nkrumah University of Science and Technology

Teaching Assistant Sep 2019 — Jun 2020
Computer Architecture, Semiconductor Devices, Engineering Technology, Basic Electronics, Embedded Systems, Digital Signal Processing
Kumasi, Ghana

ELiTE Education

Volunteer Tutor Jul 2016 — Jun 2019
Machine Learning & Hardware Programming
New York, USA
Tutored college and high school students in machine learning and hardware programming.
Talks & Presentations

Recent Presentations

  • "From Transcripts to Insights: LLM-Assisted Topic Discovery" — RTC Conference 2025 (Oral)
  • "Susu Box or Piggy Bank: Cultural Commonsense Knowledge" — EMNLP 2024, Miami, FL (Poster)
Get in Touch

Contact

I am happy to discuss research collaborations, research internship and full-time research opportunities, or any questions about my work. The best way to reach me is by email.

cacquaye AT umd.edu Google Scholar LinkedIn
University of Maryland, College Park · College Park, MD