283 citations · 2.1k across the 112 of their papers we have counts for
19 papers · 1 filter
Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework
Matthew Pisano, Peter Ly, Abraham Sanders +4
Research into AI alignment has grown considerably since the recent introduction of increasingly capable Large Language Models (LLMs). Unfortunately, modern methods of alignment sti…
Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks
Yuxuan Lu, Bingsheng Yao, Shao Zhang +5
Large Language Models (LLMs) have demonstrated considerable advances, and several claims have been made about their exceeding human performance. However, in real-world tasks, domai…
Is a Seat at the Table Enough? Engaging Teachers and Students in Dataset Specification for ML in Education
Mei Tan, Hansol Lee, Dakuo Wang +1
Despite the promises of ML in education, its adoption in the classroom has surfaced numerous issues regarding fairness, accountability, and transparency, as well as concerns about…
More Samples or More Prompts? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineering
Bingsheng Yao, Guiming Chen, Ruishi Zou +7
While most existing works on LLM prompting techniques focus only on how to select a better set of data samples inside one single prompt input (In-Context Learning or ICL), why can…
StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children's Story-Based Learning
Jiaju Chen, Yuxuan Lu, Shao Zhang +7
Interactive story reading is a common parent-child activity, where parents expect to teach both language skills and real-world knowledge beyond the story. While increasing storytel…
'Don't Get Too Technical with Me': A Discourse Structure-Based Framework for Science Journalism
Ronald Cardenas, Bingsheng Yao, Dakuo Wang +1
Science journalism refers to the task of reporting technical findings of a scientific paper as a less technical news article to the general public audience. We aim to design an aut…
Will the Prince Get True Love's Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Texts
Christina Chance, Da Yin, Dakuo Wang +1
In this paper, we study whether language models are affected by learned gender stereotypes during the comprehension of stories. Specifically, we investigate how models respond to g…
"Mango Mango, How to Let The Lettuce Dry Without A Spinner?": Exploring User Perceptions of Using An LLM-Based Conversational Assistant Toward Cooking Partner
Szeyi Chan, Jiachen Li, Bingsheng Yao +5
The rapid advancement of Large Language Models (LLMs) has created numerous potentials for integration with conversational assistants (CAs) assisting people in their daily tasks, pa…
User Interaction Patterns and Breakdowns in Conversing with LLM-Powered Voice Assistants
Amama Mahmood, Junxiang Wang, Bingsheng Yao +2
Conventional Voice Assistants (VAs) rely on traditional language models to discern user intent and respond to their queries, leading to interactions that often lack a broader conte…
Rethinking Human-AI Collaboration in Complex Medical Decision Making: A Case Study in Sepsis Diagnosis
Shao Zhang, Jianing Yu, Xuhai Xu +8
Today's AI systems for medical decision support often succeed on benchmark datasets in research papers but fail in real-world deployment. This work focuses on the decision making o…
"It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents
Zhiping Zhang, Michelle Jia, Hao-Ping Lee +5
The widespread use of Large Language Model (LLM)-based conversational agents (CAs), especially in high-stakes domains, raises many privacy concerns. Building ethical LLM-based CAs…
Talk2Care: Facilitating Asynchronous Patient-Provider Communication with Large-Language-Model
Ziqi Yang, Xuhai Xu, Bingsheng Yao +6
Despite the plethora of telehealth applications to assist home-based older adults and healthcare providers, basic messaging and phone calls are still the most common communication…
PaniniQA: Enhancing Patient Education Through Interactive Question Answering
Pengshan Cai, Zonghai Yao, Fei Liu +9
Patient portal allows discharged patients to access their personalized discharge instructions in electronic health records (EHRs). However, many patients have difficulty understand…
Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data
Xuhai Xu, Bingsheng Yao, Yuanzhe Dong +6
Advances in large language models (LLMs) have empowered a variety of applications. However, there is still a significant gap in research when it comes to understanding and enhancin…
Are Fairy Tales Fair? Analyzing Gender Bias in Temporal Narrative Event Chains of Children's Fairy Tales
Paulina Toro Isaza, Guangxuan Xu, Akintoye Oloko +3
Social biases and stereotypes are embedded in our culture in part through their presence in our stories, as evidenced by the rich history of humanities and social science literatur…
Are Human Explanations Always Helpful? Towards Objective Evaluation of Human Natural Language Explanations
Bingsheng Yao, Prithviraj Sen, Lucian Popa +2
Human-annotated labels and explanations are critical for training explainable NLP models. However, unlike human-annotated labels whose quality is easier to calibrate (e.g., with a…
Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture
Bingsheng Yao, Ishan Jindal, Lucian Popa +8
Real-world domain experts (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning tec…
Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design
Michelle S. Lam, Zixian Ma, Anne Li +4
Machine learning practitioners often end up tunneling on low-level technical details like model architectures and performance metrics. Could early model development instead focus o…
Bridging Models to Defend: A Population-Based Strategy for Robust Adversarial Defense
Ren Wang, Yuxuan Li, Can Chen +6
Adversarial robustness is a critical measure of a neural network's ability to withstand adversarial attacks at inference time. While robust training techniques have improved defens…