Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Route Sparse Autoencoder to Interpret Large Language Models
Wei Shi, Sihang Li, Tao Liang +4
Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demons…
cs.LG2025★ 1 cited
Delayed Feedback Modeling with Influence Functions
Chenlu Ding, Jiancan Wu, Yancheng Yuan +5
In online advertising under the cost-per-conversion (CPA) model, accurate conversion rate (CVR) prediction is crucial. A major challenge is delayed feedback, where conversions may…