Saved in:
Bibliographic Details
Main Authors: Bhattacharya, Paheli, Gupta, Rishabh
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.12852
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917871058157568
author Bhattacharya, Paheli
Gupta, Rishabh
author_facet Bhattacharya, Paheli
Gupta, Rishabh
contents Code explanation plays a crucial role in the software engineering domain, aiding developers in grasping code functionality efficiently. Recent work shows that the performance of LLMs for code explanation improves in a few-shot setting, especially when the few-shot examples are selected intelligently. State-of-the-art approaches for such Selective Shot Learning (SSL) include token-based and embedding-based methods. However, these SSL approaches have been evaluated on proprietary LLMs, without much exploration on open-source Code-LLMs. Additionally, these methods lack consideration for programming language syntax. To bridge these gaps, we present a comparative study and propose a novel SSL method (SSL_ner) that utilizes entity information for few-shot example selection. We present several insights and show the effectiveness of SSL_ner approach over state-of-the-art methods across two datasets. To the best of our knowledge, this is the first systematic benchmarking of open-source Code-LLMs while assessing the performances of the various few-shot examples selection approaches for the code explanation task.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12852
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Selective Shot Learning for Code Explanation
Bhattacharya, Paheli
Gupta, Rishabh
Software Engineering
Computation and Language
Information Retrieval
Code explanation plays a crucial role in the software engineering domain, aiding developers in grasping code functionality efficiently. Recent work shows that the performance of LLMs for code explanation improves in a few-shot setting, especially when the few-shot examples are selected intelligently. State-of-the-art approaches for such Selective Shot Learning (SSL) include token-based and embedding-based methods. However, these SSL approaches have been evaluated on proprietary LLMs, without much exploration on open-source Code-LLMs. Additionally, these methods lack consideration for programming language syntax. To bridge these gaps, we present a comparative study and propose a novel SSL method (SSL_ner) that utilizes entity information for few-shot example selection. We present several insights and show the effectiveness of SSL_ner approach over state-of-the-art methods across two datasets. To the best of our knowledge, this is the first systematic benchmarking of open-source Code-LLMs while assessing the performances of the various few-shot examples selection approaches for the code explanation task.
title Selective Shot Learning for Code Explanation
topic Software Engineering
Computation and Language
Information Retrieval
url https://arxiv.org/abs/2412.12852