Picture for Barbara Di Eugenio

Barbara Di Eugenio

University of Pittsburgh

Unveiling Performance Challenges of Large Language Models in Low-Resource Healthcare: A Demographic Fairness Perspective

Add code
Nov 30, 2024
Viaarxiv icon

Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks

Add code
Jul 01, 2024
Viaarxiv icon

Modeling Low-Resource Health Coaching Dialogues via Neuro-Symbolic Goal Summarization and Text-Units-Text Generation

Add code
Apr 16, 2024
Viaarxiv icon

Towards Enhancing Health Coaching Dialogue in Low-Resource Settings

Add code
Apr 13, 2024
Viaarxiv icon

A Neuro-Symbolic Approach to Monitoring Salt Content in Food

Add code
Apr 01, 2024
Viaarxiv icon

Robots Taking Initiative in Collaborative Object Manipulation: Lessons from Physical Human-Human Interaction

Add code
Apr 24, 2023
Viaarxiv icon

An End-to-End Human Simulator for Task-Oriented Multimodal Human-Robot Collaboration

Add code
Apr 02, 2023
Viaarxiv icon

Multimodal Reinforcement Learning for Robots Collaborating with Humans

Add code
Mar 13, 2023
Viaarxiv icon

Evaluating Multimodal Interaction of Robots Assisting Older Adults

Add code
Dec 20, 2022
Viaarxiv icon

Reference Resolution and Context Change in Multimodal Situated Dialogue for Exploring Data Visualizations

Add code
Sep 06, 2022
Figure 1 for Reference Resolution and Context Change in Multimodal Situated Dialogue for Exploring Data Visualizations
Figure 2 for Reference Resolution and Context Change in Multimodal Situated Dialogue for Exploring Data Visualizations
Figure 3 for Reference Resolution and Context Change in Multimodal Situated Dialogue for Exploring Data Visualizations
Figure 4 for Reference Resolution and Context Change in Multimodal Situated Dialogue for Exploring Data Visualizations
Viaarxiv icon