Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation
Source
Alex Deaconu, Anubhav Gupta, Manaal Basha, Nicholas Haydu, Gema Rodr\'iguez-P\'erez
Author
Alex Deaconu, Anubhav Gupta, Manaal Basha, Nicholas Haydu, Gema Rodr\'iguez-P\'erez
Date
Terms in this piece · Glossary
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
SWE-bench — The standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.
Why it matters
It puts measurement behind a widely repeated folk belief about prompt framing, scoring persuasion-style templates on real coding benchmarks across correctness, maintainability and security.
articleBeyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on QualityQipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu
articleBeyond the Traceback: Using LLMs for Adaptive Explanations of Programming ErrorsAlexandru-Radu Moraru, Shreyan Biswas, Ujwal Gadiraju
articleCode Health in LLM-Based Test Generation: Effectiveness and Token EfficiencyFreya Wirdemann, Markus Borg, Nadim Hagatulah, Adam Tornhill