arXiv Machine Learning
Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
Hugging Face Trending Papers
Sep 1
Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment
In many settings, studying causal questions based on text data requires adjusting for confounding information within texts. Yet there is a tradeoff in constructing text representations for adjustment:...
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
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.
arXiv Machine Learning
Jun 2
AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model Representations
arXiv:2508. 17320v3 Announce Type: replace Abstract: Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research.
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.