Where to Show Demos in Your Prompt: A Positional Bias of In-Context Learning
Kwesi A. Cobbina, Tianyi Zhou
EMNLP 2025 2025
Published
In-Context LearningLLMPrompt EngineeringNLP
Kwesi Adu Cobbina
PhD Candidate in Computer Science · University of Maryland, College Park
Advised by Prof. Tianyi Zhou and Prof. Tom Goldstein
I am a PhD candidate in Computer Science at the University of Maryland, advised by Prof. Tianyi Zhou and Prof. Tom Goldstein. My research sits at the intersection of natural language processing, multimodal learning, and optimization. I study how large language models encode and leverage in-context information — from positional biases in demonstration placement to efficient reasoning trace compression — with the goal of making LLMs more robust, efficient, and equitable.
College Park, MD · PhD expected January 2027
Research Interests
In-Context LearningLarge Language ModelsMultimodal LearningNatural Language ProcessingLLM Fairness & RobustnessOptimization
Advised by Prof. Tianyi Zhou and Prof. Tom Goldstein at University of Maryland, College Park
News
Paper accepted at EMNLP 2025: Where to Show Demos in Your Prompt: A Positional Bias of In-Context Learning.
Paper accepted at NeurIPS 2025: ColorBench: Towards Evaluation on Color Cognition Capabilities of LLMs.
Awarded M.Sc. in Computer Science from the University of Maryland, College Park.
Paper accepted at NAACL 2025: My LLM Might Mimic AAE—But When Should It?
Paper accepted at IEEE VIS 2024: Evaluating the Semantic Profiling Abilities of LLMs for Natural Language Utterances.
Received the Dean's Fellowship from the University of Maryland (2021–2023).
Joined the University of Maryland as a Graduate Research Assistant under Prof. Tianyi Zhou.
Selected Publications
* equal contribution
ColorBench: Towards Evaluation on Color Cognition Capabilities of LLMs
Yijun Liang, Ming Li, Chenrui Fan, Ziyue Li, Dang Nguyen, Kwesi A. Cobbina, Shweta Bhardwaj, Jiuhai Chen, Fuxiao Liu, Tianyi Zhou
NeurIPS 2025 2025
Published
Multimodal LearningLLM EvaluationColor CognitionBenchmark
My LLM Might Mimic AAE—But When Should It?
Sandra C. Sandoval*, Christabel Acquaye*, Kwesi A. Cobbina*, Mohammad N. Teli, Hal Daumé III
NAACL 2025 2025— * Equal contribution
Published
Language FairnessAAELLMNLPEthics
Beyond the Prompt: Approaches to Knowledge Boundary Detection in Large Language Models — A Systematic Literature Review
Brandon C. Colelough, Davis Bartels, Dina Demner-Fushman, Ishan Tamrakar, Kwesi Cobbina, Mike Ledford, Srividya Ponnada, Xinchen Yang, Yuexi Chen
IEEE TNNLS 2026— Journal article under review
Under Review
Knowledge BoundariesLLMSurveyNLP
Selected Projects
Meta-Vector: In-Context Vector Arithmetic
A test-time meta-learning approach that steers model behavior via in-context vector arithmetic, offering a practical alternative to few-shot ICL under strict context budgets. Includes a reproducible codebase and open-source toolkit (in progress).
Meta-LearningIn-Context LearningLLMPyTorch
Positional Bias Analysis Suite for ICL
An analysis suite for quantifying LLM sensitivity to demonstration ordering and placement in prompts. Supports large-scale evaluations across multiple model families and tasks, with distilled prompt-design recommendations.
In-Context LearningEvaluationPythonNLP
ChurchCast
A cross-platform mobile app enabling churches to stream services live, schedule events, and engage communities in a single unified workflow. Features push notifications, content management, and social sharing.
MobileCross-PlatformPush NotificationsContent Management
Teaching
CMSC 422
Spring 2024Introduction to Machine Learning
Teaching Assistant · University of Maryland
Supported course delivery for an upper-division undergraduate ML course covering supervised learning, neural networks, probabilistic models, and model evaluation. Held weekly office hours, graded assignments and exams, and mentored students on course projects.
Machine LearningPythonUndergraduate
CMSC 723
Fall 2023Computational Linguistics I
Teaching Assistant · University of Maryland
Assisted in a graduate-level NLP course covering language models, parsing, information extraction, and text classification. Developed and graded programming assignments; led discussion sections on transformer architectures.
NLPComputational LinguisticsGraduateTransformers
AI Curriculum
Summer 2022Project-Based AI / ML Curriculum
Curriculum Designer & Instructor · ELiTE (Emerging Labs)
Designed and delivered hands-on AI/ML curriculum for student camps and instructor training programs. Topics covered Python fundamentals, ML workflows (data processing → training → evaluation), and real-world model deployment.
AI EducationPythonML WorkflowsOutreachK-12
Service
Reviewing
- ACL Rolling Review (ARR) — 2024, 2025
- NeurIPS — 2025
- EMNLP — 2024, 2025
- NAACL — 2025
- ICML — 2025
Mentoring
- Undergraduate Research Mentor, University of Maryland (2023–present)
- AI Instructor & Mentor, ELiTE Emerging Labs (2019–2022)
Memberships
- Association for Computational Linguistics (ACL)
- Association for Computing Machinery (ACM)
Honors & Awards
Dean's Fellowship — University of Maryland, College Park
2021–2023Computer Science Department Award — GIMPA
2021College Honor Award — GIMPA
2016–2018Eroll King Fellowship — ELiTE Education
2017Contact
I am happy to discuss research collaborations, speaking opportunities, or any questions about my work. The best way to reach me is by email.
kcobbina@umd.eduUniversity of Maryland, College Park · College Park, MD