一句话:提出一套决策框架,通过正确性估计、不确定时弃权和外部验证/修复,提升代码语言模型预测的可靠性。
代码语言模型已广泛用于代码理解与生成任务,但常出现过度自信的错误预测和信心不足的正确预测,导致部署可靠性不足。论文针对实际部署所需的三项能力展开:准确估计预测正确的可能性、在不确定时弃权、以及调用外部机制验证或修复弃权输出。其核心是提出一个决策框架,统一决定何时直接回答、何时弃权,并衔接外部验证与修复,从而减少高置信错误并避免浪费正确预测。摘要未给出具体方法与实验细节。
Code language models are increasingly adopted for both understanding and generative tasks. Despite their success, these models frequently produce overconfident incorrect predictions and underconfident correct predictions, undermining their reliability in deployment. Practical deployment demands three capabilities: accurately estimating the likelihood of correctness, abstaining on uncertain predictions, and invoking external mechanisms to validate or repair abstained outputs.