SFT supplies entangled compositional traces of atomic skills and routing modules; RL identifies those modules and enables recombination on novel compositions outside the SFT support.
A versatile causal discovery framework to allow causally-related hidden variables
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
Introduces score-based causal discovery algorithms for latent variable models that achieve score equivalence and consistency while unifying some existing constraint-based approaches via degrees-of-freedom characterization.
citing papers explorer
-
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
SFT supplies entangled compositional traces of atomic skills and routing modules; RL identifies those modules and enables recombination on novel compositions outside the SFT support.
-
Score-Based Causal Discovery of Latent Variable Causal Models
Introduces score-based causal discovery algorithms for latent variable models that achieve score equivalence and consistency while unifying some existing constraint-based approaches via degrees-of-freedom characterization.