PLCLLGNov 29, 2023

Self-Infilling Code Generation

arXiv:2311.17972v36 citationsh-index: 11
Originality Incremental advance
AI Analysis

This work addresses code generation for developers by proposing a novel decoding process, though it appears incremental as it builds on existing infilling-capable models.

The paper tackles the problem of improving code generation by introducing a self-infilling framework that integrates infilling operations into auto-regressive decoding, resulting in enhanced regularity and quality across multiple benchmarks.

This work introduces self-infilling code generation, a general framework that incorporates infilling operations into auto-regressive decoding. Our approach capitalizes on the observation that recent infilling-capable code language models can self-infill: whereas infilling operations aim to fill in the middle based on a predefined prefix and suffix, self-infilling sequentially generates both such surrounding context and the infilled content. We utilize this capability to introduce novel interruption and looping mechanisms in conventional decoding, evolving it into a non-monotonic process. Interruptions allow for postponing the generation of specific code until a definitive suffix is established, enhancing control over the output. Meanwhile, the looping mechanism, which leverages the complementary nature of self-infilling and left-to-right decoding, can iteratively update and synchronize each piece of generation cyclically. Extensive experiments are conducted to demonstrate that our proposed decoding process is effective in enhancing both regularity and quality across several code generation benchmarks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes