Hugging Face Trending Papers
Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
Sep 2
Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment
arXiv:2609.01322v1 Announce Type: cross Abstract: In many settings, studying causal questions based on text data requires adjusting for confounding information within texts. Yet there is a tradeoff i...
arXiv Machine Learning
Jul 8
Learning Sparsest Linear Causal DAGs with Latent Confounders via Higher-Order Cumulants
arXiv:2607. 05984v1 Announce Type: new Abstract: Recovering the exact directed acyclic graph (DAG) in linear non-Gaussian acyclic models with latent confounders (LvLiNGAM) remains a challenging problem.
Hugging Face Trending Papers
Jul 7
Learning Sparsest Linear Causal DAGs with Latent Confounders via Higher-Order Cumulants
Recovering the exact directed acyclic graph (DAG) in linear non-Gaussian acyclic models with latent confounders (LvLiNGAM) remains a challenging problem. Although LvLiNGAM is identifiable only up to an observational equivalence class, each equivalence class is characterized by a unique sparsest DAG.
arXiv AI
Aug 6
Can Post-Training Transform LLMs into Causal Reasoners?
arXiv:2602. 06337v2 Announce Type: replace-cross Abstract: Causal inference is essential for decision-making but remains challenging for non-experts.
arXiv AI
Jun 4
Generative Augmented Inference
arXiv:2604. 14575v2 Announce Type: replace-cross Abstract: Large language models enable inexpensive AI-generated annotations, but using them reliably for causal inference remains challenging.
Hugging Face Trending Papers
Aug 13
SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization
Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on external observation. This reliance leads to superficial explanations inferred from observed model behavior and computational inefficiency from collecting such behavioral evidence at scale.