Search papers, labs, and topics across Lattice.
2
0
4
LLMs struggle to generate correct COBOL code, but a simple compilation-guided repair loop can boost success rates by over 50%.
GPT-4o can't even compile COBOL, but COBOL-Coder, a new domain-adapted LLM, achieves a 74% compilation success rate, finally bringing modern AI to legacy mainframe systems.
