SOURCE-LINKED INTELLIGENCE

Confidence-Gated Transductive Test Generation for Code Reranking

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Test case synthesis is crucial for evaluating and ranking programs generated by large language models (LLMs). However, constructing high-quality test cases remains challenging because reliable expected outputs are often difficult to obtain. We propose Confidence-Gated Transductive Test Generation (CoTT), which first uses an efficient inductive procedure and invokes transductive generation only when inductive confidence is low. This adaptive design improves output reliability while allocating extra computation only when needed. On code reranking benchmarks, CoTT outperforms prior baselines acro

Read original source ↗ Open in workspace

recordType

paper

region

Global