Tag
该论文研究代码语言模型中对 Python 的默认偏好是否由可定位的因果电路产生，通过 55 个模型-语言设置的消融、激活修补和电路提取实验发现，偏好是否显得局部化取决于探针选择与组件预算，并呼吁报告分析选择。
This paper investigates whether pre-trained code models encode type information in their hidden states, using linear probes on Java and Python examples. Results show cross-lingual type representations emerge even from untyped code, and these representations are robust to lexical perturbations and syntactic variations.
This paper introduces Code2LoRA, a hypernetwork-based method to generate adapters for code language models, addressing challenges under software evolution.
This paper investigates neural circuits in a sparse 8-layer Python transformer, finding dedicated circuitry for 106 programming concepts and decomposing them into concept-specific and token-driven components, with implications for understanding structural encoding in code models.