17 citations · 22 across the 6 of their papers we have counts for
7 papers
Lev-3B: A Data Recipe for Compact Probabilistic Log Decision Models
Leo Betthauser, Yingqi Liu, Uday Shah +5
Many log-analysis tasks involve choosing among known options, such as detecting anomalous sessions or identifying attack techniques, and benefit from calibrated probabilities. We p…
Are LLMs Good Cryptic Crossword Solvers?
Abdelrahman Sadallah, Daria Kotova, Ekaterina Kochmar
Cryptic crosswords are puzzles that rely not only on general knowledge but also on the solver's ability to manipulate language on different levels and deal with various types of wo…
Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models
Safoora Yousefi, Leo Betthauser, Hosein Hasanbeig +2
Large language models (LLMs) exhibit remarkable performance improvement through in-context learning (ICL) by leveraging task-specific examples in the input. However, the mechanisms…
ALLURE: Auditing and Improving LLM-based Evaluation of Text using Iterative In-Context-Learning
Hosein Hasanbeig, Hiteshi Sharma, Leo Betthauser +2
From grading papers to summarizing medical documents, large language models (LLMs) are evermore used for evaluation of text generated by humans and AI alike. However, despite their…
Discovering Distribution Shifts using Latent Space Representations
Leo Betthauser, Urszula Chajewska, Maurice Diesendruck +1
Rapid progress in representation learning has led to a proliferation of embedding models, and to associated challenges of model selection and practical application. It is non-trivi…
Graded persistence diagrams and persistence landscapes
Leo Betthauser, Peter Bubenik, Parker B. Edwards
We introduce a refinement of the persistence diagram, the graded persistence diagram. It is the Mobius inversion of the graded rank function, which is obtained from the rank functi…
A short note on the order of the Zhang-Liu matrices over arbitrary fields
Leo Betthauser, Josh Hiller
We give necessary and sufficient conditions for the Zhang-Liu matrices to be diagonalizable over arbitrary fields and provide the eigen-decomposition when it is possible. We use th…