Confidence-Gated Transductive Test Generation for Code Reranking

The paper introduces Confidence-Gated Transductive Test Generation (CoTT), a method that combines an efficient inductive approach with selective transductive generation triggered only when inductive confidence is low. This adaptive strategy enhances the reliability of test case outputs while limiting additional computational effort. Experiments on code reranking benchmarks demonstrate that CoTT surpasses previous baselines in performance metrics and reduces overall cost compared to applying transductive generation to every input.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• rag
• benchmarks