The test set for the TransCoder system
The TransCoder system translates source code between Java, C++, and Python 3. The test set that was used to evaluate its quality is missing important features of Java, including the ability to define and use classes and the ability to call user-defined functions other than recursively. Therefore, the accuracy of TransCoder over programs with those features remains unknown.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Transcoders Beat Sparse Autoencoders for Interpretability
Sparse autoencoders (SAEs) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from the…
Transcoders for Investigating Deception in Language Models
Transcoders have recently emerged as a promising approach for mechanistic interpretability (MI), enabling circuit-level analysis of model behaviour. In this paper, we investigate the use of transcoders to analyse decepti…
Transcoders Find Interpretable LLM Feature Circuits
A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transfo…
Transcoder-based Circuit Analysis for Interpretable Single-Cell Foundation Models
Single-cell foundation models (scFMs) have demonstrated state-of-the-art performance on various tasks, such as cell-type annotation and perturbation response prediction, by learning gene regulatory networks from large-sc…
DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
Mechanistic interpretability seeks to explain neural network behavior by decomposing model computations into interpretable features and circuits. While transcoder-based circuit tracing has recently enabled detailed causa…
Image Generation