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 impressive in-context learning (ICL)ability in code generation. LLMs take a prompt consisting of requirement-codeexamples and a new requirement as input, and output new programs. Existingstudies have found that ICL is highly dominated by the examples and thus arisesresearch on example selection. However, existing approaches randomly selectexamples or only consider the textual similarity of requirements to retrieve,leading to sub-optimal performance. In this paper, we propose a novellearning-based selection approach named LAIL (LLM-Aware In-context Learning)for code generation. Given a candidate example, we exploit LLMs themselves toestimate it by considering the generation probabilities of ground-truthprograms given a requirement and the example. We then label candidate examplesas positive or negative through the probability feedback. Based on the labeleddata, we import a contrastive learning objective to train an effectiveretriever that acquires the preference of LLMs in code generation. We applyLAIL to three LLMs and evaluate it on three representative datasets (e.g.,MBJP, MBPP, and MBCPP). LATA outperforms the state-of-the-art baselines by11.58%, 6.89%, and 5.07% on CodeGen, and 4.38%, 2.85%, and 2.74% on GPT-3.5 interms of Pass@1, respectively.

Large Language Model-Aware In-Context Learning for Code Generation