Search papers, labs, and topics across Lattice.
University of Luxembourg
2
0
3
2
Under-specifying prompts can *improve* LLM code generation correctness by breaking misleading cues that trigger incorrect retrieval-based solutions.
Turns out, a tiny fine-tuned model can spot flaws in coding instructions that trip up even the biggest LLMs, suggesting we're over-relying on brute force for code generation.
