A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
The paper introduces multicalibration to improve confidence scores in LLMs.
problem Improving the reliability and interpretability of confidence scores for LLMs.
method Forming groupings of prompt/completion pairs correlated with correctness, using clustering and self-annotation. Developing multicalibration algorithms to reduce overfitting.
result Our techniques yield confidence scores that significantly improve calibration and accuracy compared to existing methods.
The paper shows how to use proxy attributes for fairness in machine learning models with missing sensitive group data.
problem Measuring and enforcing fairness in machine learning models with incomplete sensitive group data.
method Using proxy-sensitive attributes to derive upper bounds on multiaccuracy and multicalibration violations and adjust models to satisfy these fairness notions.
result Provable upper bounds on multiaccuracy and multicalibration violations can be derived using proxy-sensitive attributes in the absence of sensitive group data.
Framework for ensuring fairness in machine learning models across multiple groups.
problem Ensuring fairness in machine learning models across multiple groups.
method Introduces (s,G,α)−GMC for multi-dimensional mappings and constraint sets, proposing algorithms to achieve multicalibration.
result Demonstrates the effectiveness of the framework on various scenarios, including image segmentation, hierarchical classification, and text generation.
As algorithms increasingly inform and influence decisions made about individuals, it becomes increasingly important to address concerns that these algorithms might be discriminatory. The output of an algorithm can be discriminatory for many reasons, most notably: (1) the data used to train the algorithm might be biased…
The paper addresses the difficulty of decision makers trusting AI-assisted predictions and proposes a method to improve confidence values.
problem Decision makers struggle to trust AI-assisted predictions based on confidence values.
method The paper investigates why decision makers have difficulties and proposes a method to construct more useful confidence values.
result Multicalibration with respect to the decision maker's confidence on her own predictions is a sufficient condition for alignment, leading to better decisions.
Comparative learning combines realizable and agnostic settings for two hypothesis classes, reducing sample complexity.
problem Learning with two hypothesis classes in a more general setting than single hypothesis classes.
method Introduces comparative learning, defines mutual VC dimension and Littlestone dimension, and applies insights to multiaccuracy and multicalibration.
result Sample complexity of comparative learning is characterized by mutual VC dimension and Littlestone dimension.