Topic modeling in new physics detection

In this work, we apply topic modeling to detect new physics in proton-proton collisions at the LHC in an unsupervised way. We investigate three new physics scenarios where fully leptonic t t ¯ → b b ¯ ℓ + ℓ − ν ℓ ν ¯ ℓ is the main source of background without relying on jet substructure variables. We demonstrate that the algorithm remains effective even in this low-particle multiplicity framework, complementing jet tagging studies, where it is typically employed. Moreover, we demonstrate that the performance of topic modeling is competitive or even better than well-known semisupervised outlier detectors, such as isolation forest and variational autoencoders, and unsupervised algorithms like Gaussian mixture models and k-means clustering with moderate and high-background pollution in almost all new physics scenarios considered.