2025
SemEval
SemEval 2025
Howard University-AI4PC at SemEval-2025 Task 8: DeepTabCoder - Code-based Retrieval and In-context Learning for Question-Answering over Tabular Data
Abstract
AbstractThis paper presents our approach, named DeepTabCoder, to SemEval 2025 - Task 8: DataBench, which focuses on question-answering over tabular data. We utilize a code-based retrieval system combined with in-context learning, which generates and executes code to answer questions, leveraging DeepSeek-V3 for code generation. DeepTabCoder outperforms the baseline, achieving accuracies of 81.42% on the DataBench dataset and 80.46% on the DataBench Lite dataset.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Computer Science and Data Science & Analytics and Natural Language Processing
Authors
Topics
Natural Language Processing > Applications > Question Answering
Computer Science > Applications > Information Retrieval
Artificial Intelligence > Core AI > Large Language Models
Machine Learning > Learning Types > In-Context Learning
Data Science & Analytics > Applications > Information Retrieval
Machine Learning > Application Areas > Information Retrieval
Artificial Intelligence > Core AI > Question Answering
Artificial Intelligence > Learning Paradigms > In-Context Learning