134 citations · 257 across the 9 of their papers we have counts for
13 papers
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…
Mixed Effects Random Forests for Personalised Predictions of Clinical Depression Severity
Robert A. Lewis, Asma Ghandeharioun, Szymon Fedor +3
This work demonstrates how mixed effects random forests enable accurate predictions of depression severity using multimodal physiological and digital activity data collected from a…
Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
Peter Hase, Mohit Bansal, Been Kim +1
Language models learn a great quantity of factual information during pretraining, and recent work localizes this information to specific model weights like mid-layer MLP weights. I…
DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
Asma Ghandeharioun, Been Kim, Chun-Liang Li +3
Explaining deep learning model inferences is a promising venue for scientific understanding, improving safety, uncovering hidden biases, evaluating fairness, and beyond, as argued…
Human-centric Dialog Training via Offline Reinforcement Learning
Natasha Jaques, Judy Hanwen Shen, Asma Ghandeharioun +5
How can we train a dialog model to produce better conversations by learning from human feedback, without the risk of humans teaching it harmful chat behaviors? We start by hosting…
Characterizing Sources of Uncertainty to Proxy Calibration and Disambiguate Annotator and Data Bias
Asma Ghandeharioun, Brian Eoff, Brendan Jou +1
Supporting model interpretability for complex phenomena where annotators can legitimately disagree, such as emotion recognition, is a challenging machine learning task. In this wor…
Hierarchical Reinforcement Learning for Open-Domain Dialog
Abdelrhman Saleh, Natasha Jaques, Asma Ghandeharioun +2
Open-domain dialog generation is a challenging problem; maximum likelihood training can lead to repetitive outputs, models have difficulty tracking long-term conversational goals,…
Towards Understanding Emotional Intelligence for Behavior Change Chatbots
Asma Ghandeharioun, Daniel McDuff, Mary Czerwinski +1
A natural conversational interface that allows longitudinal symptom tracking would be extremely valuable in health/wellness applications. However, the task of designing emotionally…
Engineering Music to Slow Breathing and Invite Relaxed Physiology
Grace Leslie, Asma Ghandeharioun, Diane Y. Zhou +1
We engineered an interactive music system that influences a user's breathing rate to induce a relaxation response. This system generates ambient music containing periodic shifts in…
Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
Natasha Jaques, Asma Ghandeharioun, Judy Hanwen Shen +5
Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critica…
Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
Asma Ghandeharioun, Judy Hanwen Shen, Natasha Jaques +4
Building an open-domain conversational agent is a challenging problem. Current evaluation methods, mostly post-hoc judgments of static conversation, do not capture conversation qua…
EMMA: An Emotion-Aware Wellbeing Chatbot
Asma Ghandeharioun, Daniel McDuff, Mary Czerwinski +1
The delivery of mental health interventions via ubiquitous devices has shown much promise. A conversational chatbot is a promising oracle for delivering appropriate just-in-time in…
Multimodal Prediction and Personalization of Photo Edits with Deep Generative Models
Ardavan Saeedi, Matthew D. Hoffman, Stephen J. DiVerdi +3
Professional-grade software applications are powerful but complicatedexpert users can achieve impressive results, but novices often struggle to complete even basic tasks. Photo…