BoolXLLM augments an existing Boolean rule learner with LLMs for feature selection, discretization thresholds, and natural-language rule translation to improve interpretability while preserving accuracy.
Nature Machine Intelligence , volume=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
A new adaptive variance estimator for relative sparsity coefficients is introduced that fully utilizes the prior asymptotic normality theorem and incorporates variable selection effects.
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
Data equity, prediction equity, and decision equity are distinct statistical requirements that need separate evaluations to address how racial biases in pulse oximetry measurements lead to treatment disparities.
A large-deviations method generates plausible stress scenarios for financial losses by concentrating on most likely configurations conditional on large losses, recovering stressed loss laws even with sparse data.
Shapley values for LLM explanations in financial text are shown via theory and experiments to produce attributions consistent with financial reasoning.
citing papers explorer
-
BoolXLLM: LLM-Assisted Explainability for Boolean Models
BoolXLLM augments an existing Boolean rule learner with LLMs for feature selection, discretization thresholds, and natural-language rule translation to improve interpretability while preserving accuracy.
-
An adaptive variance estimator for relative sparsity
A new adaptive variance estimator for relative sparsity coefficients is introduced that fully utilizes the prior asymptotic normality theorem and incorporates variable selection effects.
-
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
-
Data (in)equities in data science: Dissecting systemic and systematic biases in pulse oximetry
Data equity, prediction equity, and decision equity are distinct statistical requirements that need separate evaluations to address how racial biases in pulse oximetry measurements lead to treatment disparities.
-
Generating Plausible Stress Scenarios via Large Deviations
A large-deviations method generates plausible stress scenarios for financial losses by concentrating on most likely configurations conditional on large losses, recovering stressed loss laws even with sparse data.
-
Shapley in Context: Explaining Financial Language with Domain Expertise
Shapley values for LLM explanations in financial text are shown via theory and experiments to produce attributions consistent with financial reasoning.