Hsin‐Hsi Chen
YOU?
Author Swipe
View article: The Impact of Artificial Intelligence on the Health Economy, Workforce Productivity, and Administrative Efficiency: A Systematic Review
The Impact of Artificial Intelligence on the Health Economy, Workforce Productivity, and Administrative Efficiency: A Systematic Review Open
Background: Healthcare systems globally are under increasing financial and operational strain due to aging populations, rising expenditures, and workforce shortages. Amid these challenges, artificial intelligence (AI) has emerged as a prom…
View article: Hearing the Order: Investigating Selection Bias in Large Audio-Language Models
Hearing the Order: Investigating Selection Bias in Large Audio-Language Models Open
Large audio-language models (LALMs) are often used in tasks that involve reasoning over ordered options. An open question is whether their predictions are influenced by the order of answer choices, which would indicate a form of selection …
View article: Diagnosing Model Editing via Knowledge Spectrum
Diagnosing Model Editing via Knowledge Spectrum Open
Model editing, the process of efficiently modifying factual knowledge in pre-trained language models, is critical for maintaining their accuracy and relevance. However, existing editing methods often introduce unintended side effects, degr…
View article: Evaluating Large Language Models as Expert Annotators
Evaluating Large Language Models as Expert Annotators Open
Textual data annotation, the process of labeling or tagging text with relevant information, is typically costly, time-consuming, and labor-intensive. While large language models (LLMs) have demonstrated their potential as direct alternativ…
View article: Evaluation of performance of generative large language models for stroke care
Evaluation of performance of generative large language models for stroke care Open
Stroke is a leading cause of global morbidity and mortality, disproportionately impacting lower socioeconomic groups. In this study, we evaluated three generative LLMs—GPT, Claude, and Gemini—across four stages of stroke care: prevention, …
View article: Visual Lifelog Retrieval through Captioning-Enhanced Interpretation
Visual Lifelog Retrieval through Captioning-Enhanced Interpretation Open
People often struggle to remember specific details of past experiences, which can lead to the need to revisit these memories. Consequently, lifelog retrieval has emerged as a crucial application. Various studies have explored methods to fa…
View article: Automated Vulnerability Detection Using Deep Learning Technique
Automated Vulnerability Detection Using Deep Learning Technique Open
Our work explores the utilization of deep learning, specifically leveraging the CodeBERT model, to enhance code security testing for Python applications by detecting SQL injection vulnerabilities. Unlike traditional security testing method…
View article: Are Expert-Level Language Models Expert-Level Annotators?
Are Expert-Level Language Models Expert-Level Annotators? Open
Data annotation refers to the labeling or tagging of textual data with relevant information. A large body of works have reported positive results on leveraging LLMs as an alternative to human annotators. However, existing studies focus on …
View article: "Why" Has the Least Side Effect on Model Editing
"Why" Has the Least Side Effect on Model Editing Open
Training large language models (LLMs) from scratch is an expensive endeavor, particularly as world knowledge continually evolves. To maintain relevance and accuracy of LLMs, model editing has emerged as a pivotal research area. While these…
View article: Co-Trained Retriever-Generator Framework for Question Generation in Earnings Calls
Co-Trained Retriever-Generator Framework for Question Generation in Earnings Calls Open
In diverse professional environments, ranging from academic conferences to corporate earnings calls, the ability to anticipate audience questions stands paramount. Traditional methods, which rely on manual assessment of an audience's backg…
View article: Enhancing Investment Opinion Ranking through Argument-Based Sentiment Analysis
Enhancing Investment Opinion Ranking through Argument-Based Sentiment Analysis Open
In the era of rapid Internet and social media platform development, individuals readily share their viewpoints online. The overwhelming quantity of these posts renders comprehensive analysis impractical. This necessitates an efficient reco…
View article: Pre-Finetuning with Impact Duration Awareness for Stock Movement Prediction
Pre-Finetuning with Impact Duration Awareness for Stock Movement Prediction Open
Understanding the duration of news events' impact on the stock market is crucial for effective time-series forecasting, yet this facet is largely overlooked in current research. This paper addresses this research gap by introducing a novel…
View article: Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models
Unveiling Selection Biases: Exploring Order and Token Sensitivity in Large Language Models Open
In this paper, we investigate the phenomena of "selection biases" in Large Language Models (LLMs), focusing on problems where models are tasked with choosing the optimal option from an ordered sequence. We delve into biases related to opti…
View article: News-Driven Price Movement Forecasting with Label-Prior Graph Attention
News-Driven Price Movement Forecasting with Label-Prior Graph Attention Open
This paper introduces a novel approach to stock movement prediction using multi-label classification, leveraging the interconnections between news articles and related company stocks. We present the Label-Prior Graph Attention (LPGA) model…
View article: Fidelity-Enriched Contrastive Search: Reconciling the Faithfulness-Diversity Trade-Off in Text Generation
Fidelity-Enriched Contrastive Search: Reconciling the Faithfulness-Diversity Trade-Off in Text Generation Open
In this paper, we address the hallucination problem commonly found in natural language generation tasks. Language models often generate fluent and convincing content but can lack consistency with the provided source, resulting in potential…
View article: NumHG: A Dataset for Number-Focused Headline Generation
NumHG: A Dataset for Number-Focused Headline Generation Open
Headline generation, a key task in abstractive summarization, strives to condense a full-length article into a succinct, single line of text. Notably, while contemporary encoder-decoder models excel based on the ROUGE metric, they often fa…
View article: Large Language Models Perform Diagnostic Reasoning
Large Language Models Perform Diagnostic Reasoning Open
We explore the extension of chain-of-thought (CoT) prompting to medical reasoning for the task of automatic diagnosis. Motivated by doctors' underlying reasoning process, we present Diagnostic-Reasoning CoT (DR-CoT). Empirical results demo…
View article: Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations
Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations Open
Large language models (LLMs) have exhibited striking in-context learning (ICL) ability to adapt to target tasks with a few input-output demonstrations. For better ICL, different methods are proposed to select representative demonstrations …
View article: ZARA: Improving Few-Shot Self-Rationalization for Small Language Models
ZARA: Improving Few-Shot Self-Rationalization for Small Language Models Open
Language models (LMs) that jointly generate end-task answers as well as free-text rationales are known as self-rationalization models. Recent works demonstrate great performance gain for self-rationalization by few-shot prompting LMs with …
View article: LED: A Dataset for Life Event Extraction from Dialogs
LED: A Dataset for Life Event Extraction from Dialogs Open
Lifelogging has gained more attention due to its wide applications, such as personalized recommendations or memory assistance. The issues of collecting and extracting personal life events have emerged. People often share their life experie…