Kar Yan Tam
YOU?
Author Swipe
View article: Predicting Practically? Domain Generalization for Predictive Analytics in Real-world Environments
Predicting Practically? Domain Generalization for Predictive Analytics in Real-world Environments Open
Predictive machine learning models are widely used in customer relationship management (CRM) to forecast customer behaviors and support decision-making. However, the dynamic nature of customer behaviors often results in significant distrib…
View article: Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads
Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads Open
View article: Decentralized Voting in Product Development and Consumer Engagement: Evidence from a Blockchain-Based K-pop Community
Decentralized Voting in Product Development and Consumer Engagement: Evidence from a Blockchain-Based K-pop Community Open
View article: Decentralized Voting in Product Development and Consumer Engagement: Evidence from a Blockchain-Based K-pop Community
Decentralized Voting in Product Development and Consumer Engagement: Evidence from a Blockchain-Based K-pop Community Open
View article: Evaluating and Aligning Human Economic Risk Preferences in LLMs
Evaluating and Aligning Human Economic Risk Preferences in LLMs Open
View article: Predicting Practically? Domain Generalization for Predictive Analytics in Real-world Environments
Predicting Practically? Domain Generalization for Predictive Analytics in Real-world Environments Open
View article: LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research
LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research Open
The increasing use of text as data in social science research necessitates the development of valid, consistent, reproducible, and efficient methods for generating text-based concept measures. This paper presents a novel method that levera…
View article: Beyond Surface Similarity: Detecting Subtle Semantic Shifts in Financial Narratives
Beyond Surface Similarity: Detecting Subtle Semantic Shifts in Financial Narratives Open
In this paper, we introduce the Financial-STS task, a financial domain-specific NLP task designed to measure the nuanced semantic similarity between pairs of financial narratives. These narratives originate from the financial statements of…
View article: Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States
Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States Open
Large Language Models (LLMs) can make up answers that are not real, and this is known as hallucination. This research aims to see if, how, and to what extent LLMs are aware of hallucination. More specifically, we check whether and how an L…
View article: LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research
LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research Open
View article: Prevalence of mental disorders in adult populations from the Global South following exposure to natural hazards: a meta-analysis
Prevalence of mental disorders in adult populations from the Global South following exposure to natural hazards: a meta-analysis Open
Aims Although natural hazards (e.g., tropical cyclones, earthquakes) disproportionately affect developing countries, most research on their mental health impact has been conducted in high-income countries. We aimed to summarize prevalences…
View article: Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads
Bias A-head? Analyzing Bias in Transformer-Based Language Model Attention Heads Open
Transformer-based pretrained large language models (PLM) such as BERT and GPT have achieved remarkable success in NLP tasks. However, PLMs are prone to encoding stereotypical biases. Although a burgeoning literature has emerged on stereoty…
View article: Exploring the Relationship between In-Context Learning and Instruction Tuning
Exploring the Relationship between In-Context Learning and Instruction Tuning Open
In-Context Learning (ICL) and Instruction Tuning (IT) are two primary paradigms of adopting Large Language Models (LLMs) to downstream applications. However, they are significantly different. In ICL, a set of demonstrations are provided at…
View article: InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning
InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning Open
We present a new financial domain large language model, InvestLM, tuned on LLaMA-65B (Touvron et al., 2023), using a carefully curated instruction dataset related to financial investment. Inspired by less-is-more-for-alignment (Zhou et al.…
View article: Augmenting fake content detection in online platforms: A domain adaptive transfer learning via adversarial training approach
Augmenting fake content detection in online platforms: A domain adaptive transfer learning via adversarial training approach Open
Online platforms are experimenting with interventions such as content screening to moderate the effects of fake, biased, and incensing content. Yet, online platforms face an operational challenge in implementing machine learning algorithms…
View article: Token-Based Platforms and Green Dilemma: Examining the Role of Community Perceptions and Web Page Environmental Disclosures
Token-Based Platforms and Green Dilemma: Examining the Role of Community Perceptions and Web Page Environmental Disclosures Open
View article: Identifying the Big Shots—A Quantile-Matching Way in the Big Data Context
Identifying the Big Shots—A Quantile-Matching Way in the Big Data Context Open
The prevalence of big data has raised significant epistemological concerns in information systems research. This study addresses two of them—the deflated p -value problem and the role of explanation and prediction. To address the deflated …
View article: BARLE: Background-Aware Representation Learning for Background Shift Out-of-Distribution Detection
BARLE: Background-Aware Representation Learning for Background Shift Out-of-Distribution Detection Open
Machine learning models often suffer from a performance drop when they are applied to out-of-distribution (OOD) samples, i.e., those drawn far away from the training data distribution. Existing OOD detection work mostly focuses on identify…
View article: Model of Migration and Use of Platforms: Role of Hierarchy, Current Generation, and Complementarities in Consumer Settings
Model of Migration and Use of Platforms: Role of Hierarchy, Current Generation, and Complementarities in Consumer Settings Open
View article: Protecting Against Threats to Information Security: An Attitudinal Ambivalence Perspective
Protecting Against Threats to Information Security: An Attitudinal Ambivalence Perspective Open
A popular information security-related motivation theory is the Protection Motivation Theory (PMT) that has been studied extensively in many information security contexts with promising results. However, prior studies have found inconsiste…
View article: Managing Digital Transformation in Organizations: A Two-Stage Model and its Empirical Testing in Mandatory and Voluntary Usage Settings
Managing Digital Transformation in Organizations: A Two-Stage Model and its Empirical Testing in Mandatory and Voluntary Usage Settings Open
View article: Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graph
Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graph Open
Numeracy plays a key role in natural language understanding. However, existing NLP approaches, not only traditional word2vec approach or contextualized transformer-based language models, fail to learn numeracy. As the result, the performan…
View article: The Role of Morality in Digital Piracy: Understanding the Deterrent and Motivational Effects of Moral Reasoning in Different Piracy Contexts
The Role of Morality in Digital Piracy: Understanding the Deterrent and Motivational Effects of Moral Reasoning in Different Piracy Contexts Open
Digital piracy has been a chronic issue in intellectual property protection. With the prevalence of online technologies, digital piracy has become even more rampant, as digital resources can now be accessed and disseminated easily through …