DROPS

Artifact

Software

Chain-of-Grounded-Objectives

Authors: Sangyeop Yeo, Seung-Won Hwang, and Yu-Seung Ma

Abstract

Cite as

Sangyeop Yeo, Seung-Won Hwang, Yu-Seung Ma. Chain-of-Grounded-Objectives (Software, Source Code). Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@misc{dagstuhl-artifact-23374,
   title = {{Chain-of-Grounded-Objectives}}, 
   author = {Yeo, Sangyeop and Hwang, Seung-Won and Ma, Yu-Seung},
   note = {Software, version 1.0., swhId: \href{https://archive.softwareheritage.org/swh:1:dir:315704008a9f9a515047943266a959518485cbb0}{\texttt{swh:1:dir:315704008a9f9a515047943266a959518485cbb0}} (visited on 2025-06-25)},
   url = {https://github.com/DDIDUs/Chain-of-Grounded-Objectives},
   doi = {10.4230/artifacts.23374},
}

Document

DOI: 10.4230/LIPIcs.ECOOP.2025.35

Chain of Grounded Objectives: Concise Goal-Oriented Prompting for Code Generation

Authors: Sangyeop Yeo, Seung-Won Hwang, and Yu-Seung Ma

Published in: LIPIcs, Volume 333, 39th European Conference on Object-Oriented Programming (ECOOP 2025)

Abstract

The use of Large Language Models (LLMs) for code generation has gained significant attention in recent years. Existing methods often aim to improve the quality of generated code by incorporating additional contextual information or guidance into input prompts. Many of these approaches adopt process-oriented reasoning strategies, mimicking human-like step-by-step thinking; however, they may not always align with the structured nature of programming languages. This paper introduces Chain of Grounded Objectives (CGO), a concise goal-oriented prompting approach that embeds functional objectives into prompts to enhance code generation. By focusing on precisely defined objectives rather than explicit procedural steps, CGO aligns more naturally with programming tasks while retaining flexibility. Empirical evaluations on HumanEval, MBPP, their extended versions, and LiveCodeBench show that CGO achieves accuracy comparable to or better than existing methods while using fewer tokens, making it a more efficient approach to LLM-based code generation.

Cite as

Sangyeop Yeo, Seung-Won Hwang, and Yu-Seung Ma. Chain of Grounded Objectives: Concise Goal-Oriented Prompting for Code Generation. In 39th European Conference on Object-Oriented Programming (ECOOP 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 333, pp. 35:1-35:25, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{yeo_et_al:LIPIcs.ECOOP.2025.35,
  author =	{Yeo, Sangyeop and Hwang, Seung-Won and Ma, Yu-Seung},
  title =	{{Chain of Grounded Objectives: Concise Goal-Oriented Prompting for Code Generation}},
  booktitle =	{39th European Conference on Object-Oriented Programming (ECOOP 2025)},
  pages =	{35:1--35:25},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-373-7},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{333},
  editor =	{Aldrich, Jonathan and Silva, Alexandra},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECOOP.2025.35},
  URN =		{urn:nbn:de:0030-drops-233271},
  doi =		{10.4230/LIPIcs.ECOOP.2025.35},
  annote =	{Keywords: Artificial Intelligence, Natural Language Processing, Prompt Design, Large Language Models, Code Generation}
}

Search Results

Documents authored by Yeo, Sangyeop

Chain-of-Grounded-Objectives

Abstract

Cite as

Chain of Grounded Objectives: Concise Goal-Oriented Prompting for Code Generation

Abstract

Cite as

Thanks for your feedback!

Could not send message