Butler, Landon

4 publications

NeurIPS 2025 ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs Landon Butler, Abhineet Agarwal, Justin Singh Kang, Yigit Efe Erginbas, Bin Yu, Kannan Ramchandran

ICML 2025 SPEX: Scaling Feature Interaction Explanations for LLMs Justin Singh Kang, Landon Butler, Abhineet Agarwal, Yigit Efe Erginbas, Ramtin Pedarsani, Bin Yu, Kannan Ramchandran

ICLRW 2025 SPEX: Scaling Feature Interaction Explanations for LLMs Justin Singh Kang, Landon Butler, Abhineet Agarwal, Yigit Efe Erginbas, Ramtin Pedarsani, Bin Yu, Kannan Ramchandran

NeurIPS 2024 Learning to Understand: Identifying Interactions via the Möbius Transform Justin Singh Kang, Yigit Efe Erginbas, Landon Butler, Ramtin Pedarsani, Kannan Ramchandran