Summary of Transcoders Find Interpretable Llm Feature Circuits, by Jacob Dunefsky and Philippe Chlenski and Neel Nanda
Transcoders Find Interpretable LLM Feature Circuitsby Jacob Dunefsky, Philippe Chlenski, Neel NandaFirst submitted to arxiv…
Transcoders Find Interpretable LLM Feature Circuitsby Jacob Dunefsky, Philippe Chlenski, Neel NandaFirst submitted to arxiv…
GAugLLM: Improving Graph Contrastive Learning for Text-Attributed Graphs with Large Language Modelsby Yi Fang, Dongzhe…
Decomposed evaluations of geographic disparities in text-to-image modelsby Abhishek Sureddy, Dishant Padalia, Nandhinee Periyakaruppa, Oindrila…
Delay Embedding Theory of Neural Sequence Modelsby Mitchell Ostrow, Adam Eisen, Ila FieteFirst submitted to…
Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Plannerby Kenneth Li,…
The Benefits and Risks of Transductive Approaches for AI Fairnessby Muhammed Razzak, Andreas Kirsch, Yarin…
Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantizationby Seungwoo Son, Wonpyo…
Sparsity-Constraint Optimization via Splicing Iterationby Zezhi Wang, Jin Zhu, Junxian Zhu, Borui Tang, Hongmei Lin,…
LiLiuM: eBay’s Large Language Models for e-commerceby Christian Herold, Michael Kozielski, Leonid Ekimov, Pavel Petrushkov,…
Large Scale Transfer Learning for Tabular Data via Language Modelingby Josh Gardner, Juan C. Perdomo,…