arXiv subjects

Sijia Yang

Publications and source records attributed to Sijia Yang.

At least 19 recordsLinked to original sources

arXiv2025

DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents

Accurately modeling opinion change through social interactions is crucial for understanding and mitigating polarization, misinformation, and societal conflict. Recent work simulates opinion dynamics with role-playing LLM agents (RPLAs), but multi-agent simulations often display unnatural group behavior, such as premature convergence, and lack empirical benchmarks for assessing alignment with real human group interactions. We introduce DEBATE, a large-scale benchmark for evaluating the authenticity of opinion dynamics in multi-agent RPLA simulations. DEBATE contains multi-round public messages and private Likert-scale beliefs from U.S.-based participants across 107 topics; the cleaned benchmark used in our experiments contains 2,788 participants in 697 groups, enabling evaluation at the utterance and group levels and supporting future individual-level analyses. We instantiate "digital twin" RPLAs with seven LLMs and evaluate across two settings: next-message prediction and full dynamics simulation, using stance-based opinion-dynamics metrics. In zero-shot settings, RPLA groups exhibit strong opinion convergence relative to human groups. On the held-out group split, supervised fine-tuning (SFT) for Llama-3.1-8B-Instruct improves auxiliary stance alignment and reduces group-level convergence error, though discrepancies in opinion change and belief updating remain. DEBATE enables rigorous benchmarking of simulated opinion dynamics and supports future research on aligning multi-agent RPLAs with realistic human interactions.

cs.CL↗

arXiv2024

Optimizing Social Media Annotation of HPV Vaccine Skepticism and Misinformation Using Large Language Models: An Experimental Evaluation of In-Context Learning and Fine-Tuning Stance Detection Across Multiple Models

This paper leverages large-language models (LLMs) to experimentally determine optimal strategies for scaling up social media content annotation for stance detection on HPV vaccine-related tweets. We examine both conventional fine-tuning and emergent in-context learning methods, systematically varying strategies of prompt engineering across widely used LLMs and their variants (e.g., GPT4, Mistral, and Llama3, etc.). Specifically, we varied prompt template design, shot sampling methods, and shot quantity to detect stance on HPV vaccination. Our findings reveal that 1) in general, in-context learning outperforms fine-tuning in stance detection for HPV vaccine social media content; 2) increasing shot quantity does not necessarily enhance performance across models; and 3) different LLMs and their variants present differing sensitivity to in-context learning conditions. We uncovered that the optimal in-context learning configuration for stance detection on HPV vaccine tweets involves six stratified shots paired with detailed contextual prompts. This study highlights the potential and provides an applicable approach for applying LLMs to research on social media stance and skepticism detection.

cs.CL↗

arXiv2024

Purrfessor: A Fine-tuned Multimodal LLaVA Diet Health Chatbot

This study introduces Purrfessor, an innovative AI chatbot designed to provide personalized dietary guidance through interactive, multimodal engagement. Leveraging the Large Language-and-Vision Assistant (LLaVA) model fine-tuned with food and nutrition data and a human-in-the-loop approach, Purrfessor integrates visual meal analysis with contextual advice to enhance user experience and engagement. We conducted two studies to evaluate the chatbot's performance and user experience: (a) simulation assessments and human validation were conducted to examine the performance of the fine-tuned model; (b) a 2 (Profile: Bot vs. Pet) by 3 (Model: GPT-4 vs. LLaVA vs. Fine-tuned LLaVA) experiment revealed that Purrfessor significantly enhanced users' perceptions of care ($\beta = 1.59$, $p = 0.04$) and interest ($\beta = 2.26$, $p = 0.01$) compared to the GPT-4 bot. Additionally, user interviews highlighted the importance of interaction design details, emphasizing the need for responsiveness, personalization, and guidance to improve user engagement.

cs.HC↗

arXiv2024

Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks

Creating human-like large language model (LLM) agents is crucial for faithful social simulation. Having LLMs role-play based on demographic information sometimes improves human likeness but often does not. This study assessed whether LLM alignment with human behavior can be improved by integrating information from empirically-derived human belief networks. Using data from a human survey, we estimated a belief network encompassing 64 topics loading on nine non-overlapping latent factors. We then seeded LLM-based agents with an opinion on one topic, and assessed the alignment of its expressed opinions on remaining test topics with corresponding human data. Role-playing based on demographic information alone did not align LLM and human opinions, but seeding the agent with a single belief greatly improved alignment for topics related in the belief network, and not for topics outside the network. These results suggest a novel path for human-LLM belief alignment in work seeking to simulate and understand patterns of belief distributions in society.

cs.CL↗

arXiv2024

Simulating Opinion Dynamics with Networks of LLM-based Agents

Accurately simulating human opinion dynamics is crucial for understanding a variety of societal phenomena, including polarization and the spread of misinformation. However, the agent-based models (ABMs) commonly used for such simulations often over-simplify human behavior. We propose a new approach to simulating opinion dynamics based on populations of Large Language Models (LLMs). Our findings reveal a strong inherent bias in LLM agents towards producing accurate information, leading simulated agents to consensus in line with scientific reality. This bias limits their utility for understanding resistance to consensus views on issues like climate change. After inducing confirmation bias through prompt engineering, however, we observed opinion fragmentation in line with existing agent-based modeling and opinion dynamics research. These insights highlight the promise and limitations of LLM agents in this domain and suggest a path forward: refining LLMs with real-world discourse to better simulate the evolution of human beliefs.

physics.soc-ph↗

arXiv2024

The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents

Human groups are able to converge on more accurate beliefs through deliberation, even in the presence of polarization and partisan bias -- a phenomenon known as the "wisdom of partisan crowds." Generated agents powered by Large Language Models (LLMs) are increasingly used to simulate human collective behavior, yet few benchmarks exist for evaluating their dynamics against the behavior of human groups. In this paper, we examine the extent to which the wisdom of partisan crowds emerges in groups of LLM-based agents that are prompted to role-play as partisan personas (e.g., Democrat or Republican). We find that they not only display human-like partisan biases, but also converge to more accurate beliefs through deliberation as humans do. We then identify several factors that interfere with convergence, including the use of chain-of-thought prompt and lack of details in personas. Conversely, fine-tuning on human data appears to enhance convergence. These findings show the potential and limitations of LLM-based agents as a model of human collective intelligence.

cs.CL↗

arXiv2023

Natural Language based Context Modeling and Reasoning for Ubiquitous Computing with Large Language Models: A Tutorial

Large language models (LLMs) have become phenomenally surging, since 2018--two decades after introducing context-awareness into computing systems. Through taking into account the situations of ubiquitous devices, users and the societies, context-aware computing has enabled a wide spectrum of innovative applications, such as assisted living, location-based social network services and so on. To recognize contexts and make decisions for actions accordingly, various artificial intelligence technologies, such as Ontology and OWL, have been adopted as representations for context modeling and reasoning. Recently, with the rise of LLMs and their improved natural language understanding and reasoning capabilities, it has become feasible to model contexts using natural language and perform context reasoning by interacting with LLMs such as ChatGPT and GPT-4. In this tutorial, we demonstrate the use of texts, prompts, and autonomous agents (AutoAgents) that enable LLMs to perform context modeling and reasoning without requiring fine-tuning of the model. We organize and introduce works in the related field, and name this computing paradigm as the LLM-driven Context-aware Computing (LCaC). In the LCaC paradigm, users' requests, sensors reading data, and the command to actuators are supposed to be represented as texts. Given the text of users' request and sensor data, the AutoAgent models the context by prompting and sends to the LLM for context reasoning. LLM generates a plan of actions and responds to the AutoAgent, which later follows the action plan to foster context-awareness. To prove the concepts, we use two showcases--(1) operating a mobile z-arm in an apartment for assisted living, and (2) planning a trip and scheduling the itinerary in a context-aware and personalized manner.

cs.CL↗

arXiv2023

Constructing Vec-tionaries to Extract Message Features from Texts: A Case Study of Moral Appeals

While researchers often study message features like moral content in text, such as party manifestos and social media, their quantification remains a challenge. Conventional human coding struggles with scalability and intercoder reliability. While dictionary-based methods are cost-effective and computationally efficient, they often lack contextual sensitivity and are limited by the vocabularies developed for the original applications. In this paper, we present an approach to construct vec-tionary measurement tools that boost validated dictionaries with word embeddings through nonlinear optimization. By harnessing semantic relationships encoded by embeddings, vec-tionaries improve the measurement of message features from text, especially those in short format, by expanding the applicability of original vocabularies to other contexts. Importantly, a vec-tionary can produce additional metrics to capture the valence and ambivalence of a message feature beyond its strength in texts. Using moral content in tweets as a case study, we illustrate the steps to construct the moral foundations vec-tionary, showcasing its ability to process texts missed by conventional dictionaries and word embedding methods and to produce measurements better aligned with crowdsourced human assessments. Furthermore, additional metrics from the vec-tionary unveiled unique insights that facilitated predicting outcomes such as message retransmission.

cs.CL↗

arXiv2023

Evolving Domain Adaptation of Pretrained Language Models for Text Classification

Adapting pre-trained language models (PLMs) for time-series text classification amidst evolving domain shifts (EDS) is critical for maintaining accuracy in applications like stance detection. This study benchmarks the effectiveness of evolving domain adaptation (EDA) strategies, notably self-training, domain-adversarial training, and domain-adaptive pretraining, with a focus on an incremental self-training method. Our analysis across various datasets reveals that this incremental method excels at adapting PLMs to EDS, outperforming traditional domain adaptation techniques. These findings highlight the importance of continually updating PLMs to ensure their effectiveness in real-world applications, paving the way for future research into PLM robustness against the natural temporal evolution of language.

cs.CL↗

arXiv2023

Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AI

Generative AI models like DALL-E 2 can interpret textual prompts and generate high-quality images exhibiting human creativity. Though public enthusiasm is booming, systematic auditing of potential gender biases in AI-generated images remains scarce. We addressed this gap by examining the prevalence of two occupational gender biases (representational and presentational biases) in 15,300 DALL-E 2 images spanning 153 occupations, and assessed potential bias amplification by benchmarking against 2021 census labor statistics and Google Images. Our findings reveal that DALL-E 2 underrepresents women in male-dominated fields while overrepresenting them in female-dominated occupations. Additionally, DALL-E 2 images tend to depict more women than men with smiling faces and downward-pitching heads, particularly in female-dominated (vs. male-dominated) occupations. Our computational algorithm auditing study demonstrates more pronounced representational and presentational biases in DALL-E 2 compared to Google Images and calls for feminist interventions to prevent such bias-laden AI-generated images to feedback into the media ecology.

cs.CV↗

arXiv2023

Improving Covariance-Regularized Discriminant Analysis for EHR-based Predictive Analytics of Diseases

Linear Discriminant Analysis (LDA) is a well-known technique for feature extraction and dimension reduction. The performance of classical LDA, however, significantly degrades on the High Dimension Low Sample Size (HDLSS) data for the ill-posed inverse problem. Existing approaches for HDLSS data classification typically assume the data in question are with Gaussian distribution and deal the HDLSS classification problem with regularization. However, these assumptions are too strict to hold in many emerging real-life applications, such as enabling personalized predictive analysis using Electronic Health Records (EHRs) data collected from an extremely limited number of patients who have been diagnosed with or without the target disease for prediction. In this paper, we revised the problem of predictive analysis of disease using personal EHR data and LDA classifier. To fill the gap, in this paper, we first studied an analytical model that understands the accuracy of LDA for classifying data with arbitrary distribution. The model gives a theoretical upper bound of LDA error rate that is controlled by two factors: (1) the statistical convergence rate of (inverse) covariance matrix estimators and (2) the divergence of the training/testing datasets to fitted distributions. To this end, we could lower the error rate by balancing the two factors for better classification performance. Hereby, we further proposed a novel LDA classifier De-Sparse that leverages De-sparsified Graphical Lasso to improve the estimation of LDA, which outperforms state-of-the-art LDA approaches developed for HDLSS data. Such advances and effectiveness are further demonstrated by both theoretical analysis and extensive experiments on EHR datasets.

cs.LG↗

arXiv2023

Adoption and implication of the Biased-Annotator Competence Estimation (BACE) model into COVID-19 vaccine Twitter data: Human annotation for latent message features

Traditional quantitative content analysis approach (human coding method) has weaknesses, such as assuming all human coders are equally accurate once the intercoder reliability for training reaches a threshold score. We applied the Biased-Annotator Competence Estimation (BACE) model (Tyler, 2021), which draws on Bayesian modeling to improve human coding. An important contribution of this model is it takes each coder's potential biases and reliability into consideration and treats the "true" label of each message as a latent parameter, with quantifiable estimation uncertainties. In contrast, in conventional human coding, each message will receive a fixed label without estimates for measurement uncertainties. In this extended abstract, we first summarize the weaknesses of conventional human coding; and then apply the BACE model to COVID-19 vaccine Twitter data and compare BACE with other statistical models; finally, we discuss how the BACE model can be applied to improve human coding of latent message features.

stat.AP↗

arXiv2022

Broadband Terahertz Quantum Cascade Laser Dual-Comb Sources with Off-Resonant Microwave Injection

Broadband dual-comb spectroscopy has attracted increasing interests due to its unique advantages in high spectral resolution, fast detection, and so on. Although the dual-comb technique is relatively mature in the infrared wavelengths, it is, currently, not commercially capable of practical applications in the terahertz regime due to the lack of high performance broadband terahertz dual-comb sources. In the terahertz frequency range, the electrically pumped quantum cascade laser (QCL) is a suitable candidate for the dual-comb operation. However, free running terahertz QCL dual-comb sources normally show limited optical bandwidths ($\sim$100-200 GHz). Although the resonant microwave injection locking has been widely used to broaden the emission spectra of terahertz QCLs by modulating the laser drive current at the cavity round-trip frequency, it is hard to be employed to broaden the dual-comb bandwidths due to the large phase noise induced by the resonant injection and non-ideal microwave circuits. Therefore, it is challenging to obtain broadband terahertz dual-comb sources that can fully exploits the laser gain bandwidth. Here, we employ an off-resonant microwave injection to significantly broaden the dual-comb bandwidth of a terahertz QCL dual-comb source emitting around 4.2 THz. The measured optical dual-comb bandwidth is broadened from 147 GHz in free running to $>$450 GHz under the off-resonant injection. The broadened dual-comb bandwidth is experimentally proved by the transmission measurements of a filter and a GaAs etalon. By performing a simple numerical analysis based on a rate equation model, we explain that the broadband dual-comb operation under the off-resonant microwave injection could be resulted from a wider lasing bandwidth and a higher degree of phase matching.

physics.optics↗

arXiv2022

From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques

Mobile Sensing Apps have been widely used as a practical approach to collect behavioral and health-related information from individuals and provide timely intervention to promote health and well-beings, such as mental health and chronic cares. As the objectives of mobile sensing could be either \emph{(a) personalized medicine for individuals} or \emph{(b) public health for populations}, in this work we review the design of these mobile sensing apps, and propose to categorize the design of these apps/systems in two paradigms -- \emph{(i) Personal Sensing} and \emph{(ii) Crowd Sensing} paradigms. While both sensing paradigms might incorporate with common ubiquitous sensing technologies, such as wearable sensors, mobility monitoring, mobile data offloading, and/or cloud-based data analytics to collect and process sensing data from individuals, we present a novel taxonomy system with two major components that can specify and classify apps/systems from aspects of the life-cycle of mHealth Sensing: \emph{(1) Sensing Task Creation \& Participation}, \emph{(2) Health Surveillance \& Data Collection}, and \emph{(3) Data Analysis \& Knowledge Discovery}. With respect to different goals of the two paradigms, this work systematically reviews this field, and summarizes the design of typical apps/systems in the view of the configurations and interactions between these two components. In addition to summarization, the proposed taxonomy system also helps figure out the potential directions of mobile sensing for health from both personalized medicines and population health perspectives.

cs.LG↗

arXiv2021

Data Placement for Multi-Tenant Data Federation on the Cloud

Due to privacy concerns of users and law enforcement in data security and privacy, it becomes more and more difficult to share data among organizations. Data federation brings new opportunities to the data-related cooperation among organizations by providing abstract data interfaces. With the development of cloud computing, organizations store data on the cloud to achieve elasticity and scalability for data processing. The existing data placement approaches generally only consider one aspect, which is either execution time or monetary cost, and do not consider data partitioning for hard constraints. In this paper, we propose an approach to enable data processing on the cloud with the data from different organizations. The approach consists of a data federation platform named FedCube and a Lyapunov-based data placement algorithm. FedCube enables data processing on the cloud. We use the data placement algorithm to create a plan in order to partition and store data on the cloud so as to achieve multiple objectives while satisfying the constraints based on a multi-objective cost model. The cost model is composed of two objectives, i.e., reducing monetary cost and execution time. We present an experimental evaluation to show our proposed algorithm significantly reduces the total cost (up to 69.8\%) compared with existing approaches.

cs.DC↗

arXiv2021

Active Stabilization of Terahertz Semiconductor Dual-Comb Laser Sources Employing a Phase Locking Technique

Dual-comb sources with equally spaced and low phase noise frequency lines are of great importance for high resolution spectroscopy and metrology. In the terahertz frequency range, electrically pumped semiconductor quantum cascade lasers (QCLs) are suitable candidates for frequency comb and dual-comb operation. For a single laser frequency comb, the repetition rate can be locked using a microwave injection locking and the carrier frequency can be locked to a highly stable source. However, for the locking of two laser combs, four frequencies (two repetition rates and two carrier offset frequencies) should be simultaneously locked; If one only refers to the dual-comb signal, two relative frequencies, i.e., the offset frequency and repetition frequency of one laser against those of the other laser, should be locked. Although the locking techniques that have been successfully used for a single laser comb can be, in principle, applied to a dual-comb laser source, the complete locking considerably complicates the implementation of such a system. Here, we propose a method to stabilize a terahertz QCL dual-comb source by phase locking one of the dual-comb lines to a radio frequency (RF) synthesizer. This technique forces one of the lasers to follow the tone of the other one (keeping the sum of the carrier offset frequency difference and repetition frequency difference between the two laser combs as a constant) by exploiting a laser self-detection that avoids the use of an external detector. Through the demonstration of this locking technique, we demonstrate that the dual-comb can generate periodic pulses over a 2 us time scale, showing that the terahertz QCL comb without a control of the repetition rate can produce pulsed-type waveforms.

physics.app-ph↗

arXiv2020

Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good

Developing intelligent persuasive conversational agents to change people's opinions and actions for social good is the frontier in advancing the ethical development of automated dialogue systems. To do so, the first step is to understand the intricate organization of strategic disclosures and appeals employed in human persuasion conversations. We designed an online persuasion task where one participant was asked to persuade the other to donate to a specific charity. We collected a large dataset with 1,017 dialogues and annotated emerging persuasion strategies from a subset. Based on the annotation, we built a baseline classifier with context information and sentence-level features to predict the 10 persuasion strategies used in the corpus. Furthermore, to develop an understanding of personalized persuasion processes, we analyzed the relationships between individuals' demographic and psychological backgrounds including personality, morality, value systems, and their willingness for donation. Then, we analyzed which types of persuasion strategies led to a greater amount of donation depending on the individuals' personal backgrounds. This work lays the ground for developing a personalized persuasive dialogue system.

cs.CL↗

arXiv2019

Towards Compact and Real-Time Terahertz Dual-Comb Spectroscopy Employing a Self-Detection Scheme

Due to its fast and high resolution characteristics, dual-comb spectroscopy has attracted an increasing amount of interest since its first demonstration. In the terahertz frequency range where abundant absorption lines (finger prints) of molecules are located, multiheterodyne spectroscopy that employs the dual-comb technique shows an advantage in real-time spectral detection over the traditional Fourier transform infrared or time domain spectroscopies. Here, we demonstrate compact terahertz dual-comb spectroscopy based on quantum cascade lasers (QCLs). In our experiment, two free-running QCLs generate approximately 120 GHz wide combs centered at 4.2 THz, with slightly different repetition frequencies. We observe that $\sim$490 nW terahertz power coupling of one laser into the other suffices for laser-self-detecting the dual-comb spectrum that is registered by a microwave spectrum analyzer. Furthermore, we demonstrate practical terahertz transmission dual-comb spectroscopy with our device, by implementing a short air path at room temperature. Spectra are shown of semiconductor samples and of moist air, the latter allowing rapid monitoring of the relative humidity. Our devices should be readily extendable to perform imaging, microscopy and near-field microscopy in the terahertz regime.

physics.optics↗