English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large Language Models (LLMs) have shown great success in code generation.LLMs take as the input a prompt and output the code. A key question is how tomake prompts (i.e., Prompting Techniques). Existing prompting techniques aredesigned for natural language generation and have low accuracy in codegeneration.  In this paper, we propose a new prompting technique named AceCoder. Ourmotivation is that code generation meets two unique challenges (i.e.,requirement understanding and code implementation). AceCoder contains two novelmechanisms (i.e., guided code generation and example retrieval) to solve thesechallenges. (1) Guided code generation asks LLMs first to analyze requirementsand output an intermediate preliminary (e.g., test cases). The preliminary isused to clarify requirements and tell LLMs "what to write". (2) Exampleretrieval selects similar programs as examples in prompts, which provide lotsof relevant content (e.g., algorithms, APIs) and teach LLMs "how to write". Weapply AceCoder to three LLMs (e.g., Codex) and evaluate it on three publicbenchmarks using the Pass@k. Results show that AceCoder can significantlyimprove the performance of LLMs on code generation. (1) In terms of Pass@1,AceCoder outperforms the state-of-the-art baseline by up to 56.4% in MBPP,70.7% in MBJP, and 88.4% in MBJSP. (2) AceCoder is effective in LLMs withdifferent sizes (i.e., 6B to 13B) and different languages (i.e., Python, Java,and JavaScript). (3) Human evaluation shows human developers prefer programsfrom AceCoder.

AceCoder: Utilizing Existing Code to Enhance Code Generation