Search papers, labs, and topics across Lattice.
4
0
5
5
Evolved prompt transformation rules can fix 10-30% of LLM code generation failures, outperforming traditional execution-feedback methods.
Faulty code can bias LLM-generated tests, reducing fault detection effectiveness by nearly half when tests are generated after the code.
LLMs can produce coherent but fundamentally misaligned code due to a phenomenon called detrimental semantic collapse, affecting over 10% of tasks in standard benchmarks.
Prompt Coverage Adequacy uncovers over 30% more faults than traditional code coverage, revolutionizing how we test LLM-generated code.
