Publications (18)
TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations
Dylan Slack, Satyapriya Krishna, Himabindu Lakkaraju +1
Machine Learning (ML) models are increasingly used to make critical decisions in real-world applications, yet they have become more complex, making them harder to understand. To th…
Learning Goal-Conditioned Representations for Language Reward Models
Vaskar Nath, Dylan Slack, Jeff Da +4
Techniques that learn improved representations via offline data or self-supervised objectives have shown impressive results in traditional reinforcement learning (RL). Nevertheless…
Counterfactual Explanations Can Be Manipulated
Dylan Slack, Sophie Hilgard, Himabindu Lakkaraju +1
Counterfactual explanations are emerging as an attractive option for providing recourse to individuals adversely impacted by algorithmic decisions. As they are deployed in critical…
Towards physician-centered oversight of conversational diagnostic AI
Elahe Vedadi, David Barrett, Natalie Harris +32
Recent work has demonstrated the promise of conversational AI systems for diagnostic dialogue. However, real-world assurance of patient safety means that providing individual diagn…
Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data
Dylan Slack, Sorelle Friedler, Emile Givental
Motivated by concerns surrounding the fairness effects of sharing and transferring fair machine learning tools, we propose two algorithms: Fairness Warnings and Fair-MAML. The firs…
Defuse: Harnessing Unrestricted Adversarial Examples for Debugging Models Beyond Test Accuracy
Dylan Slack, Nathalie Rauschmayr, Krishnaram Kenthapadi
We typically compute aggregate statistics on held-out test data to assess the generalization of machine learning models. However, statistics on test data often overstate model gene…
Differentially Private Language Models Benefit from Public Pre-training
Gavin Kerrigan, Dylan Slack, Jens Tuyls
Language modeling is a keystone task in natural language processing. When training a language model on sensitive information, differential privacy (DP) allows us to quantify the de…
Reliable Post hoc Explanations: Modeling Uncertainty in Explainability
Dylan Slack, Sophie Hilgard, Sameer Singh +1
As black box explanations are increasingly being employed to establish model credibility in high-stakes settings, it is important to ensure that these explanations are accurate and…
Fair Meta-Learning: Learning How to Learn Fairly
Dylan Slack, Sorelle Friedler, Emile Givental
Data sets for fairness relevant tasks can lack examples or be biased according to a specific label in a sensitive attribute. We demonstrate the usefulness of weight based meta-lear…
Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods
Dylan Slack, Sophie Hilgard, Emily Jia +2
As machine learning black boxes are increasingly being deployed in domains such as healthcare and criminal justice, there is growing emphasis on building tools and techniques for e…
Assessing the Local Interpretability of Machine Learning Models
Dylan Slack, Sorelle A. Friedler, Carlos Scheidegger +1
The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpret…
On the Lack of Robust Interpretability of Neural Text Classifiers
Muhammad Bilal Zafar, Michele Donini, Dylan Slack +3
With the ever-increasing complexity of neural language models, practitioners have turned to methods for understanding the predictions of these models. One of the most well-adopted…
Feature Attributions and Counterfactual Explanations Can Be Manipulated
Dylan Slack, Sophie Hilgard, Sameer Singh +1
As machine learning models are increasingly used in critical decision-making settings (e.g., healthcare, finance), there has been a growing emphasis on developing methods to explai…
A Careful Examination of Large Language Model Performance on Grade School Arithmetic
Hugh Zhang, Jeff Da, Dean Lee +12
Large language models (LLMs) have achieved impressive success on many benchmarks for mathematical reasoning. However, there is growing concern that some of this performance actuall…
SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition
Dylan Slack, Yinlam Chow, Bo Dai +1
Methods that extract policy primitives from offline demonstrations using deep generative models have shown promise at accelerating reinforcement learning(RL) for new tasks. Intuiti…
Post Hoc Explanations of Language Models Can Improve Language Models
Satyapriya Krishna, Jiaqi Ma, Dylan Slack +3
Large Language Models (LLMs) have demonstrated remarkable capabilities in performing complex tasks. Moreover, recent research has shown that incorporating human-annotated rationale…
TABLET: Learning From Instructions For Tabular Data
Dylan Slack, Sameer Singh
Acquiring high-quality data is often a significant challenge in training machine learning (ML) models for tabular prediction, particularly in privacy-sensitive and costly domains l…
Rethinking Explainability as a Dialogue: A Practitioner's Perspective
Himabindu Lakkaraju, Dylan Slack, Yuxin Chen +2
As practitioners increasingly deploy machine learning models in critical domains such as health care, finance, and policy, it becomes vital to ensure that domain experts function e…