Where to Show Demos in Your Prompt: A Positional Bias of In-Context Learning
Kwesi A. Cobbina, Tianyi Zhou
Empirical Methods in Natural Language Processing (EMNLP) 2025
Published
In-Context LearningLLMPrompt EngineeringNLP
Publications
9 total · 4 published · 5 in progress · * equal contribution
Showing 9 of 9 publications
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
Conference on Neural Information Processing Systems (NeurIPS) 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
Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) 2025— * Equal contribution
Published
Language FairnessAAELLMNLPEthics
Evaluating the Semantic Profiling Abilities of LLMs for Natural Language Utterances
Hannah K. Bako, Arshnoor Bhutani, Xinyi Liu, Kwesi A. Cobbina, Zhicheng Liu
IEEE Visualization and Visual Analytics (VIS) 2024
Published
VisualizationNLPLLM EvaluationSemantic Analysis
V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions
Chenrui Fan, Yijun Liang, Shweta Bhardwaj, Ming Li, Kwesi A. Cobbina, Tianyi Zhou
Conference on Computer Vision and Pattern Recognition (CVPR) 2026— Under review
Under Review
Visual ReasoningMultimodalBenchmarkVision-Language
Efficient Reasoning Trace
Kwesi A. Cobbina, Ming Li*, Dang Nguyen, Chenguang Wang, Tianyi Zhou
Association for Computational Linguistics (ACL) 2026— Manuscript in preparation
In Preparation
ReasoningLLMEfficiencyNLP
Flip-Rate No More: Position-Aware Controllers for Prompt Robustness
Kwesi A. Cobbina*, Simran Gawri, Tianyi Zhou
Association for Computational Linguistics (ACL) 2026— Manuscript in preparation
In Preparation
Prompt RobustnessLLMIn-Context LearningNLP
Meta-Vector: Test-Time Meta-Learning via In-Context Vector Arithmetic
Kwesi A. Cobbina*, Yuhan Wang*, Tianyi Zhou
International Conference on Machine Learning (ICML) 2026— Manuscript in preparation
In Preparation
Meta-LearningIn-Context LearningLLMOptimization
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 Transactions on Neural Networks and Learning Systems (TNNLS) 2026— Journal article under review
Under Review
Knowledge BoundariesLLMSurveyNLP