2026-10-15T07:51:06Z https://api.figshare.com/v2/oai

oai:figshare.com:article/30846323 2026-07-28T11:15:26Z category_29179 category_28846 portal_845 item_type_3 month_year_07_2026

B4: Towards optimal assessment of plausible code solutions with plausible tests Mouxiang Chen (22818278) Liu Zhongxin (22818287) Tao He (22818292) Hong Yusu (22818297) David LO (8645202) Xin Xia (21176876) Jiangling Sun (22818350) Automated software engineering Modelling and simulation Code solutions assessment Software creation and management Code generation Bayesian framework approach <p dir="ltr">Dataset for paper "B4: Towards optimal assessment of plausible code solutions with plausible tests".</p><p dir="ltr">Selecting the best code solution from multiple generated ones is an essential task in code generation, which can be achieved by using some reliable validators (<i>e.g.</i>, developer-written test cases) for assistance. Since reliable test cases are not always available and can be expensive to build in practice, researchers propose to automatically generate test cases to assess code solutions. However, when both code solutions and test cases are plausible and not reliable, selecting the best solution becomes challenging. Although some heuristic strategies have been proposed to tackle this problem, they lack a strong theoretical guarantee and it is still an open question whether an optimal selection strategy exists. Our work contributes in two ways. First, we show that within a Bayesian framework, the optimal selection strategy can be defined based on the posterior probability of the observed passing states between solutions and tests. The problem of identifying the best solution is then framed as an integer programming problem. Second, we propose an efficient approach for approximating this optimal (yet uncomputable) strategy, where the approximation error is bounded by the correctness of prior knowledge. We then incorporate effective prior knowledge to tailor code generation tasks. Both theoretical and empirical studies confirm that existing heuristics are limited in selecting the best solutions with plausible test cases. Our proposed approximated optimal strategy <i>ℬ</i>⁴ significantly surpasses existing heuristics in selecting code solutions generated by large language models (LLMs) with LLM-generated tests, achieving a relative performance improvement by up to 50% over the strongest heuristic and 246% over the random selection in the most challenging scenarios.</p> 2024-09-09T08:07:37Z Dataset Dataset 10.5281/zenodo.13737381 https://figshare.com/articles/dataset/B4_Towards_optimal_assessment_of_plausible_code_solutions_with_plausible_tests/30846323 CC BY 4.0