SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.09136 · ACL · 2024

DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning

Pei Wang, Muxi Diao, Guanting Dong, Weihao Zeng, Yejie Wang, Weiran Xu, Jingang Wang, Xunliang Cai, Keqing He, Mengdi Zhang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Code Large Language Models (Code LLMs) have demonstrated outstanding performance in code-related tasks. Several instruction tuning approaches have been proposed to boost the code generation performance of pre-trained Code LLMs. In this paper, we introduce a diverse instruction model (DolphCoder) with self-evaluating for code generation. It learns diverse instruction targets and combines a code evaluation objective to enhance its code generation ability. Our model achieves superior performance on the HumanEval and MBPP benchmarks, demonstrating new insights for future code instruction tuning work. Our key findings are: (1) Augmenting more diverse responses with distinct reasoning paths increases the code capability of LLMs. (2) Improving one's ability to evaluate the correctness of code solutions also enhances their ability to create it. Our code is released at https://github.com/prisnlp/DolphCoder. Response 2 Bubble Sort...

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.09136")
get_code_for_paper("2402.09136")
have("2402.09136")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.09136.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.09136.svg)](https://syntology.ai/paper/2402.09136)

Connect an agent — have() is free.