Chain of Grounded Objectives: Concise Goal-oriented Prompting for Code Generation
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.
Wed 2 JulDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
16:15 - 17:39 | |||
16:15 21mTalk | Automatic Goal Clone Detection in Rocq Technical Papers Ali Ghanbari Auburn University | ||
16:36 21mTalk | Contract Usage and Evolution in Android Mobile Applications Technical Papers David R. Ferreira Faculty of Engineering, University of Porto, Alexandra Mendes Faculty of Engineering, University of Porto & INESC TEC, João F. Ferreira INESC-ID and IST, University of Lisbon, Carolina Carreira Carnegie Mellon University, IST University of Lisbon, INESC-ID | ||
16:57 21mTalk | Chain of Grounded Objectives: Concise Goal-oriented Prompting for Code Generation Technical Papers Sangyeop Yeo ETRI (Electronics and Telecommunications Research Institute), seung-won hwang Seoul National University, Yu-Seung Ma Electronics and Telecommunications Research Institute | ||
17:18 21mTalk | Contract Systems Need Domain-Specific Notations Technical Papers Cameron Moy Northeastern University, Ryan Jung PLT @ Northeastern University, Matthias Felleisen Northeastern University |