按年被提到
20232023 · 2 次2026
软件工程与 AI 编程›代码生成与程序合成·arXiv:2304.10423 · cs.SE

Fully Autonomous Programming with Large Language Models

Vadim Liventsev, Anastasiia Grishina, Aki Härmä, Leon Moonen · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-04-22 · 最近 2023-05-07
2不同的人
2活跃月份
2讨论串
48被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Current approaches to program synthesis with Large Language Models (LLMs) exhibit a "near miss syndrome": they tend to generate programs that semantically resemble the correct answer (as measured by text similarity metrics or human evaluation), but achieve a low or even zero accuracy as measured by unit tests due to small imperfections, such as the wrong input or output format. This calls for an approach known as Synthesize, Execute, Debug (SED), whereby a draft of the solution is generated first, followed by a program repair phase addressing the failed tests. To effectively apply this approach to instruction-driven LLMs, one needs to determine which prompts perform best as instructions for LLMs, as well as strike a balance between repairing unsuccessful programs and replacing them with newly generated ones. We explore these trade-offs empirically, comparing replace-focused, repair-focused, and hybrid debug strategies, as well as different template-based and model-based prompt-generation techniques. We use OpenAI Codex as the LLM and Program Synthesis Benchmark 2 as a database of problem descriptions and tests for evaluation. The resulting framework outperforms both conventional usage of Codex without the repair phase and traditional genetic programming approaches.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论vok · 2023-05

“Push has remained active for genetic programming, and there's recent work comparing program synthesis with language models vs. PushGP: https://arxiv.org/pdf/2304.10423.pdf”

Push 3.0 Programming Language Description (2004)原评论 ↗
被提交为 story · 1 次