Biblio Discovery — Demo Discovery Service

1 hasil untuk "Lim, Soohan"

Menampilkan 1–1 · 0,15 detik · RSS

  1. Preprint Teks lengkap

    ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code Generation

    Lim, Soohan; Hahn, Joonghyuk; Park, Hyunwoo dkk.

    arXiv · 2025 · Inggris · arXiv

    Current code generation evaluation measures functional correctness on well-formed inputs that satisfy all input preconditions. This paradigm has a critical limitation: task descriptions often leave these preconditions implicit, while evaluation filters out inputs that violate them. As a result…