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 promising results in automatic codegeneration by improving coding efficiency to a certain extent. However,generating high-quality and reliable code remains a formidable task because ofLLMs' lack of good programming practice, especially in exception handling. Inthis paper, we first conduct an empirical study and summarise three crucialchallenges of LLMs in exception handling, i.e., incomplete exception handling,incorrect exception handling and abuse of try-catch. We then try prompts withdifferent granularities to address such challenges, finding fine-grainedknowledge-driven prompts works best. Based on our empirical study, we propose anovel Knowledge-driven Prompt Chaining-based code generation approach, nameKPC, which decomposes code generation into an AI chain with iterativecheck-rewrite steps and chains fine-grained knowledge-driven prompts to assistLLMs in considering exception-handling specifications. We evaluate ourKPC-based approach with 3,079 code generation tasks extracted from the Javaofficial API documentation. Extensive experimental results demonstrate that theKPC-based approach has considerable potential to ameliorate the quality of codegenerated by LLMs. It achieves this through proficiently managing exceptionsand obtaining remarkable enhancements of 109.86% and 578.57% with staticevaluation methods, as well as a reduction of 18 runtime bugs in the sampleddataset with dynamic validation.

From Misuse to Mastery: Enhancing Code Generation with Knowledge-Driven AI Chaining