PromptResponse: Optimizing Prompts for LLM Coding Tasks
Large language models (LLMs) are increasingly used in research workflows and software development pipelines, yet their output remains sensitive to input prompt variations. This paper presents $\unicode{x00AB}$PromptResponse$\unicode{x00BB}$, a controlled study examining how formatting and LLM-based tuning of coding task prompts affect the resulting code's performance, efficiency, and stability. Using five semantically identical yet syntactically distinct variants of the HumanEval dataset$\unicode{x2014}$baseline, JSON, Markdown, YAML, and an LLM-tuned version$\unicode{x2014}$we had GPT-4o solv
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 56%A system-level approach to prompt injection: separating instruction and data channels in LLM agents [P] →
- PossiblePossibly related (embedding) · 49%Preparing data for supervised fine-tuning Part 1: Formatting and quality →
- LinkedLinked via arxiv author · 85%Erik Thureck →
“PromptResponse: Optimizing Prompts for LLM Coding Tasks”
- LinkedLinked via arxiv author · 85%Robert Kühnen →
“PromptResponse: Optimizing Prompts for LLM Coding Tasks”
- LinkedLinked via arxiv author · 85%Tim Jacobowitz →
“PromptResponse: Optimizing Prompts for LLM Coding Tasks”
- FuzzySimilar title/name (fuzzy) · 87%f/prompts.chat →
“Fuzzy title match (0.94): “PromptResponse: Optimizing Prompts for LLM Coding Tasks” ≈ “f/prompts.chat””
- FuzzySimilar title/name (fuzzy) · 59%NirDiamant/Prompt_Engineering →
“Fuzzy title match (0.73): “PromptResponse: Optimizing Prompts for LLM Coding Tasks” ≈ “NirDiamant/Prompt_Engineering””
- FuzzySimilar title/name (fuzzy) · 59%linshenkx/prompt-optimizer →
“Fuzzy title match (0.73): “PromptResponse: Optimizing Prompts for LLM Coding Tasks” ≈ “linshenkx/prompt-optimizer””