Function-Level Execution Feedback for Code Preference Optimization
Source
Idris Nechnech, Sehwan Kim, Jimin Seo, Yeongoon Kim, Minhae Oh, Sangwoo Hong, Jungwoo Lee
Author
Idris Nechnech, Sehwan Kim, Jimin Seo, Yeongoon Kim, Minhae Oh, Sangwoo Hong, Jungwoo Lee
Date
Terms in this piece · Glossary
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
Execution beats judgment when labeling code correctness: LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition →-as-a-judge annotations systematically mark working functions as failures, corrupting the preference data that execution-based labels get right.
articleCode Health in LLM-Based Test Generation: Effectiveness and Token EfficiencyFreya Wirdemann, Markus Borg, Nadim Hagatulah, Adam Tornhill
articleCompiler-Guided Adaptive Proof Search with Cross-Model Synergy on Context-Dependent Theorem ProvingZhuo Liu, Ding Yu, Hangfeng He
articleAuditing and Decomposing Feedback-Driven Evolution in LLM Test Generation under the Oracle ProblemYunhao Liang, Chengguang Gan, Ruixuan Ying, Hanjun Wei, Zhe Cui, Shiwen Ni