activity
20172024
most citedThink before you act: A simple baseline for compositional generalization

9 citations · 26 across the 8 of their papers we have counts for

collaborators

11 papers

cs.AI2024

Do LLMs estimate uncertainty well in instruction-following?

Juyeon Heo, Miao Xiong, Christina Heinze-Deml +1

Large language models (LLMs) could be valuable personal AI agents across various domains, provided they can precisely follow user instructions. However, recent studies have shown s…

cs.AI2024★ 1 cited

Do LLMs "know" internally when they follow instructions?

Juyeon Heo, Christina Heinze-Deml, Oussama Elachqar +5

Instruction-following is crucial for building AI agents with large language models (LLMs), as these models must adhere strictly to user-provided constraints and guidelines. However…

stat.ME2022

Characterization and Greedy Learning of Gaussian Structural Causal Models under Unknown Interventions

Juan L. Gamella, Armeen Taeb, Christina Heinze-Deml +1

We consider the problem of recovering the causal structure underlying observations from different experimental conditions when the targets of the interventions in each experiment a…

stat.ME2021★ 1 cited

Learning and scoring Gaussian latent variable causal models with unknown additive interventions

Armeen Taeb, Juan L. Gamella, Christina Heinze-Deml +1

With observational data alone, causal structure learning is a challenging problem. The task becomes easier when having access to data collected from perturbations of the underlying…

cs.LG2020★ 9 cited

Think before you act: A simple baseline for compositional generalization

Christina Heinze-Deml, Diane Bouchacourt

Contrarily to humans who have the ability to recombine familiar expressions to create novel ones, modern neural networks struggle to do so. This has been emphasized recently with t…

stat.ME2020★ 5 cited

Active Invariant Causal Prediction: Experiment Selection through Stability

Juan L. Gamella, Christina Heinze-Deml

A fundamental difficulty of causal learning is that causal models can generally not be fully identified based on observational data only. Interventional data, that is, data origina…