5 papers
T-FIX: Text-Based Explanations with Features Interpretable to eXperts
Shreya Havaldar, Weiqiu You, Chaehyeon Kim +12
As LLMs are deployed in knowledge-intensive settings (e.g., surgery, astronomy, therapy), users are often domain experts who expect not just answers, but explanations that mirror p…
Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups
Weiqiu You, Helen Qu, Marco Gatti +2
Self-attributing neural networks (SANNs) present a potential path towards interpretable models for high-dimensional problems, but often face significant trade-offs in performance.…
The FIX Benchmark: Extracting Features Interpretable to eXperts
Helen Jin, Shreya Havaldar, Chaehyeon Kim +10
Feature-based methods are commonly used to explain model predictions, but these methods often implicitly assume that interpretable features are readily available. However, this is…
Dimensionality Reduction Techniques for Statistical Inference in Cosmology
Minsu Park, Marco Gatti, Bhuvnesh Jain
We explore linear and non-linear dimensionality reduction techniques for statistical inference of parameters in cosmology. Given the importance of compressing the increasingly comp…
At First Sight: Zero-Shot Classification of Astronomical Images with Large Multimodal Models
Dimitrios Tanoglidis, Bhuvnesh Jain
Vision-Language multimodal Models (VLMs) offer the possibility for zero-shot classification in astronomy: i.e. classification via natural language prompts, with no training. We inv…