Abstract.Large Language Models (LLMs) can take on personas that provide culturally informed advisor-client conversations that facilitate mental health therapy. This paper is a comparative study of bilingual, persona-based therapeutic conversations created by LLMs in the person of either a client or a counselor. We will compare an English-speaking big brother (Raoul) and a Chinese auntie persona ("Aunt Mei" or Mei Yi) in conversations concerning depression. We will use quantitative linguistic analysis, tracking sentiment trajectory, an exploratory self-disclosure scoring system, and a lexicon of … Read more →

Abstract.Academic record authentication plays a pivotal role in enhancing university students' comprehensive employability and revitalizing their personal learning experiences as credible digital assets. Based on the practical needs of academic record authentication and its convergence with blockchain technology, this paper designs a model for a blockchain-based academic record authentication management system. It systematically elaborates on the functional design and implementation methods across various layers of the system architecture, with a focus on the composite blockchain ledger structure and … Read more →

Abstract.The proliferation of large language models (LLMs) in critical applications has intensified concerns about embedded social biases that can perpetuate discrimination and inequality. While numerous bias mitigation techniques have been proposed, systematic comparison of intervention timing pacifically in-training versus post-training approaches remains limited. This paper presents a comprehensive empirical evaluation of bias mitigation strategies across six LLM architectures ranging from 340 million to 1.7 trillion parameters. We implement and compare four in-training methods (data preprocessing, … Read more →

Abstract.With the rapid development of digital multimedia technology, images, as an important carrier of information dissemination, have been widely applied in fields such as healthcare, security, commerce, and social networking. However, images are highly susceptible to tampering, duplication, and illegal use during transmission and storage, posing severe challenges to their authenticity and integrity. Traditional image authentication techniques exhibit significant deficiencies in terms of security, robustness, and invisibility, making them difficult to meet the increasing security demands. This paper … Read more →

Abstract.This project focuses on predicting used car prices using a combination of data preprocessing, unsupervised learning, and advanced supervised learning techniques [1, 2]. The goal was to develop an accurate model for price prediction by exploring patterns in vehicle features and leveraging robust machine learning methodologies. The dataset was meticulously cleaned and enhanced by imputing missing values using a random forest-based imputation method [3], splitting multi-dimensional features such as engine specifications, and categorizing variables like brand and transmission types. Principal … Read more →

Abstract.The core essence of constructing the "Big Ideological-Political Course" lies in advancing ideological and political education from a "closed classroom" to a "social field." Red research-based learning (RRL), as a key bridge linking the "small classroom" with the "large social classroom," finds its educational efficacy constrained by multiple factors, including resource supply, curriculum design, and implementation guarantees. Currently, RRL practices commonly face a "coordination failure" dilemma, characterized by high synergistic barriers between government, universities, and social … Read more →