← Search

Jonathan Smith

2 accepted papers

2026

Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset

ICLR 2026poster

How can large language models (LLMs) serve users with varying preferences that may conflict across cultural, political, or other dimensions? To advance this challenge, this paper establishes four key results. First, we demonstrate, through a large-scale multilingual human study with representative s…

Cited by 0SourcecodeScholar
2023

Temporal Dependencies in Feature Importance for Time Series Prediction

ICLR 2023poster

Time series data introduces two key challenges for explainability methods: firstly, observations of the same feature over subsequent time steps are not independent, and secondly, the same feature can have varying importance to model predictions over time. In this paper, we propose Windowed Feature I…

Cited by 26SourcePDFScholar