Papers by Hung To
Functional Overlap Reranking for Neural Code Generation (2024.findings-acl)
Copied to clipboard
| Challenge: | Code Large Language Models (CodeLLMs) have ushered in a new era in code generation, but selecting the best code solutions remains a challenge. |
| Approach: | They propose a new reranking strategy that quantifies the functional overlap between solution clusters to provide a better ranking strategy for code solutions. |
| Outcome: | Empirical results show that the proposed method surpasses state-of-the-art methods on the pass@1 score. |
Better Language Models of Code through Self-Improvement (2023.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models for code (PLMCs) are pre-taught on large datasets with multi-modal objectives, but fine-tuning them requires extensive supervision and is limited by the size of the dataset provided. |
| Approach: | They propose a data augmentation framework that utilizes knowledge from the pre-training and fine-tuning stage to augment training data, which is then used for the next step. |
| Outcome: | The proposed framework significantly improves pre-trained language models’ performance in sequence-generation tasks, such as code summarization and code generation in the CodeXGLUE benchmark. |