Generating executable code from natural language instructions using Large Language Models (LLMs) poses challenges such as semantic ambiguity and understanding taskspecific contexts. To address these issues, we propose a system called DemoCraft, which enhances code generation by leveraging in-context learning and demonstration selection, combined with latent concept learning. Latent concept learning introduces additional concept tokens, which are trainable embeddings that capture task-specific knowledge. We then test our system on two major datasets: MBPP and Humaneval. Our experimental results demonstrate that the proposed system achieves an approximate 2x increase in the pass@k metric compared to baseline models. Furthermore, we introduce two novel evaluation metrics: correctness@k and similarity@k. Our empirical studies indicate that our system attains nearly a 3x improvement in these metrics as well.
View on arXiv@article{kapu2025_2411.00865,
title={ Demo-Craft: Using In-Context Learning to Improve Code Generation in Large Language Models },
author={ Nirmal Joshua Kapu and Mihit Sreejith },
journal={arXiv preprint arXiv:2411.00865},
year={ 2025 }
}