Julie Shah
3 papers in the PaperMetrix corpus
Papers by this author
-
Bayes-Probe: Distribution-Guided Sampling for Prediction Level Sets.
2020 · arXiv (Cornell University)
Post-hoc explanation methods are gaining popularity for interpreting, understanding, and debugging neural networks. Most analyses using such methods explain decisions in response to inputs drawn from the test set. However, the test set may have …
-
An Information Bottleneck Characterization of the Understanding-Workload Tradeoff
2023 · arXiv (Cornell University)
Recent advances in artificial intelligence (AI) have underscored the need for explainable AI (XAI) to support human understanding of AI systems. Consideration of human factors that impact explanation efficacy, such as mental workload and human …
-
Grounding Language Plans in Demonstrations Through Counterfactual Perturbations
2024 · arXiv (Cornell University)
Grounding the common-sense reasoning of Large Language Models (LLMs) in physical domains remains a pivotal yet unsolved problem for embodied AI. Whereas prior works have focused on leveraging LLMs directly for planning in symbolic spaces, …