77 citations · 114 across the 12 of their papers we have counts for
12 papers
The Asymmetric Harms of LLM Compression
Yuan Wu, Mairui Li, Lesia Semenova +1
Large language models (LLMs) compression reduces deployment costs, but standard aggregate metrics like perplexity and accuracy often mask underlying behavioral shifts. In this work…
Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods
Michal Moshkovitz, Suraj Srinivas, Lesia Semenova +7
Despite the proliferation of Explainable AI (XAI) techniques -- from feature attributions to sparse autoencoders -- explanations rarely influence real-world workflows. In practice,…
The Double-Edged Nature of the Rashomon Set for Trustworthy Machine Learning
Ethan Hsu, Harry Chen, Chudi Zhong +1
Real-world machine learning (ML) pipelines rarely produce a single model; instead, they produce a Rashomon set of many near-optimal ones. We show that this multiplicity reshapes ke…
Parameter-Efficient Construction of the Rashomon Slice for Concept Bottleneck Models
Shihan Feng, Cheng Zhang, Michael Xi +3
In many machine learning problems, there may exist multiple models that achieve nearly identical predictive performance while relying on fundamentally different internal logic. How…
This EEG Looks Like These EEGs: Interpretable Interictal Epileptiform Discharge Detection With ProtoEEG-kNN
Dennis Tang, Jon Donnelly, Alina Jade Barnett +8
The presence of interictal epileptiform discharges (IEDs) in electroencephalogram (EEG) recordings is a critical biomarker of epilepsy. Even trained neurologists find detecting IED…
Amazing Things Come From Having Many Good Models
Cynthia Rudin, Chudi Zhong, Lesia Semenova +7
The Rashomon Effect, coined by Leo Breiman, describes the phenomenon that there exist many equally good predictive models for the same dataset. This phenomenon happens for many rea…
ProtoEEGNet: An Interpretable Approach for Detecting Interictal Epileptiform Discharges
Dennis Tang, Frank Willard, Ronan Tegerdine +8
In electroencephalogram (EEG) recordings, the presence of interictal epileptiform discharges (IEDs) serves as a critical biomarker for seizures or seizure-like events.Detecting IED…
Fast and Interpretable Mortality Risk Scores for Critical Care Patients
Chloe Qinyu Zhu, Muhang Tian, Lesia Semenova +4
Prediction of mortality in intensive care unit (ICU) patients typically relies on black box models (that are unacceptable for use in hospitals) or hand-tuned interpretable models (…
A Path to Simpler Models Starts With Noise
Lesia Semenova, Harry Chen, Ronald Parr +1
The Rashomon set is the set of models that perform approximately equally well on a given dataset, and the Rashomon ratio is the fraction of all models in a given hypothesis space t…
Multitask Learning for Citation Purpose Classification
Alex Oesterling, Angikar Ghosal, Haoyang Yu +4
We present our entry into the 2021 3C Shared Task Citation Context Classification based on Purpose competition. The goal of the competition is to classify a citation in a scientifi…
Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges
Cynthia Rudin, Chaofan Chen, Zhi Chen +3
Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel…
On the Existence of Simpler Machine Learning Models
Lesia Semenova, Cynthia Rudin, Ronald Parr
It is almost always easier to find an accurate-but-complex model than an accurate-yet-simple model. Finding optimal, sparse, accurate models of various forms (linear models with in…