Macro uses Direct Preference Optimization on composite-scored preference pairs to improve validity of multilingual self-generated counterfactual explanations by 12.55% on average without degrading minimality.
The annals of mathematical statistics , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
An information-theoretic DII framework extracts low-dimensional nuclear modes governing conical intersection access and non-radiative decay from high-dimensional nonadiabatic dynamics simulations across multiple molecular systems.
citing papers explorer
-
Enhancing Multilingual Counterfactual Generation through Alignment-as-Preference Optimization
Macro uses Direct Preference Optimization on composite-scored preference pairs to improve validity of multilingual self-generated counterfactual explanations by 12.55% on average without degrading minimality.
-
Machine learning the non-radiative decay modes in photochemical processes
An information-theoretic DII framework extracts low-dimensional nuclear modes governing conical intersection access and non-radiative decay from high-dimensional nonadiabatic dynamics simulations across multiple molecular systems.