From the 1 of 5 linked papers with an AI index.
5 papers
Bet on Features: Anytime-Valid and Feature-Aware Auditing of Conditional Quantile Forecasters
Ivane Antonov, Sohom Mukherjee, Richard Pibernik +1
The paper proposes a distribution‑free, game‑theoretic framework for continuously auditing black‑box conditional quantile forecasters, allowing the auditor to detect miscalibration…
Betting on Bets: Anytime-Valid Tests for Stochastic Dominance
Sebastian Arnold, Yo Joong Choe, Marco Scarsini +1
How can we monitor, in real time, whether one uncertain prospect has any upside over another? To answer this question, we develop a novel family of sequential, anytime-valid tests…
The Information Geometry of Softmax: Probing and Steering
Kiho Park, Todd Nief, Yo Joong Choe +1
This paper concerns the question of how AI systems encode semantic structure into the geometric structure of their representation spaces. The motivating observation is that the nat…
Combining Evidence Across Filtrations
Yo Joong Choe, Aaditya Ramdas
In sequential anytime-valid inference, any admissible procedure must be based on e-processes: generalizations of test martingales that quantify the accumulated evidence against a c…
The Geometry of Categorical and Hierarchical Concepts in Large Language Models
Kiho Park, Yo Joong Choe, Yibo Jiang +1
The linear representation hypothesis is the informal idea that semantic concepts are encoded as linear directions in the representation spaces of large language models (LLMs). Prev…