AI RESEARCH
The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation
arXiv CS.AI
•
ArXi:2606.04057v1 Announce Type: cross Large language models (LLMs) now generate substantial production code, often for tasks with multiple valid algorithmic solutions. Incidental prompt cues, meaning contextual words or metadata outside the task specification, can steer which algorithm the model selects, even when all outputs pass the same tests. Prompt sensitivity is well studied as a tool to improve output quality. Here, output policy means algorithm choice under fixed correctness.