9 июл. 2024 г. · The results reveal that LLMs perform suboptimally when summarizing code written in logic programming languages compared to other language types.

Recent advancements in large language models (LLMs) have significantly enhanced their ability to understand both natural language and code, driving their use in ...

Use IBM Granite models to summarize code and generate descriptions or comments automatically.

20 мая 2024 г. · Large language models (LLMs) such as Llama 2 perform very well on tasks that involve both natural language and source code, particularly code ...

PromptCS trains a prompt agent that can generate continuous prompts to unleash the potential for LLMs in code summarization. 9. 26 Dec 2023.

Code for the paper "Analyzing the Performance of Large Language Models on Code Summarization" accepted in LREC-COLING 2024.

Code summarization is helpful, because developers spend around 59% of their time comprehending or understanding others' work or their own prior works [24]. Good ...

We propose Project Context for Code Summarization with LLMs (ProConSuL), a new framework to provide a large language model (LLM) with precise information ...

Code summarization is the task of comprehending source code and automatically generating concise natural language descriptions for it.

This result suggests that LLMs like Codex are really sample-efficient. All the baselines are fine-tuned with 24K-251K for each language, whereas the LLM ...