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: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.
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:2602. 06337v2 Announce Type: replace-cross Abstract: Causal inference is essential for decision-making but remains challenging for non-experts.
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.
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:2606. 08496v1 Announce Type: cross Abstract: Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse features, explaining these features still remains a central challenge.
Counterfactual (CF) explanations identify changes that alter an input's classification. While existing methods produce realistic and low-cost CFs, they often fail to ensure feasibility, by suggesting...
arXiv:2508. 17320v3 Announce Type: replace Abstract: Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research.
iFlip is an iterative refinement method for generating counterfactual examples using large language models. It incorporates three feedback types—model confidence, feature attribution, and natural language—to guide successive edits. Experiments show iFlip outperforms five state‑of‑the‑art baselines, achieving a 57.8% higher validity rate and improving model performance through counterfactual data augmentation.
arXiv:2404.06349v3 Announce Type: replace Abstract: The ability to understand causality significantly impacts the competence of large language models (LLMs) in output explanation and counterfactual r...
arXiv:2601.08058v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting often improves the reasoning performance of large language models (LLMs), but the internal signal that trigg...