2 citations · 4 across the 4 of their papers we have counts for
3 papers · 1 filter
Debiasing Reward Models by Representation Learning with Guarantees
Ignavier Ng, Patrick Blöbaum, Siddharth Bhandari +2
Recent alignment techniques, such as reinforcement learning from human feedback, have been widely adopted to align large language models with human preferences by learning and leve…
From Guess2Graph: When and How Can Unreliable Experts Safely Boost Causal Discovery in Finite Samples?
Sujai Hiremath, Dominik Janzing, Philipp Faller +4
Causal discovery algorithms often perform poorly with limited samples. While integrating expert knowledge (including from LLMs) as constraints promises to improve performance, guar…
Causal vs. Anticausal merging of predictors
Sergio Hernan Garrido Mejia, Patrick Blöbaum, Bernhard Schölkopf +1
We study the differences arising from merging predictors in the causal and anticausal directions using the same data. In particular we study the asymmetries that arise in a simple…