FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

[+] Add paper CodePatchLLM by dsshay · Pull Request #122 · ml4code/ml4code.github.io · GitHub

/ ml4code.github.io Public

[+] Add paper CodePatchLLM #122

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dsshay wants to merge 1 commit into
base: source
Choose a base branch
Could not load branches
Branch not found: {{ refName }}

Are you sure you want to change the base?

Some commits from the old base branch may be removed from the timeline, and old review comments may become outdated.
from
Conversation 0 Commits 1 Checks 0 Files changed
Open

[+] Add paper CodePatchLLM #122

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension .markdown  (1) All 1 file type selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
12 changes: 12 additions & 0 deletions _publications/shaikhelislamov2024codepatchllm.markdown
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
---
layout: publication
title: "CodePatchLLM: Configuring code generation using a static analyzer"
authors: Danil Shaikhelislamov, Mikhail Drobyshevskiy, Andrey Belevantsev
conference: KDD2024
year: 2024
additional_links:
- {name: "website", url: "https://genai-evaluation-kdd2024.github.io/genai-evalution-kdd2024/assets/papers/GenAI_Evaluation_KDD2024_paper_25.pdf"}
- {name: "code", url: "https://github.com/dsshay/CodePatchLLM"}
tags: ["LLM", "static analysis", "verification"]
---
The development of large language models (LM) has significantly advanced the field of code generation. A survey of developers by Stack Overflow has found that 70% of respondents are using or plan to use AI coding tools this year. Current approaches mainly rely on supervised fine-tuning objectives borrowed from text generation, neglecting unique sequence-level characteristics of code, including but not limited to compilability as well as syntactic and functional correctness. To address this limitation, we propose a new approach to code generation that synergistically combines pre-trained LLM models with software analysis tools, which are widely used to check or vulnerabilities while validating the code. By utilizing expanded messages from code compilation and analysing, proposed approach seamlessly integrates external code-specific knowledge into the prompt chaining process. We develop CodePatchLLM, an extension for LLM that utilizes Svace feedback for code generation. It is important to note that CodePatchLLM is a model-agnostic framework that can be used across different program languages. Extensive experiments on LeetCode dataset demonstrate the effectiveness of our proposed approach compared to backbone model, CodeLlama, achieving significant improvements in compilation success rates and functional correctness across Java, Python and Kotlin languages. Our CodePatchLLM code is available online: https://github.com/dsshay/CodePatchLLM
Back | FazBrowse Home | New Git URL