arXiv subjects

Jiyou Jia

Publications and source records attributed to Jiyou Jia.

9 recordsLinked to original sources

arXiv2026

Tracing GenAI Literacy: Uncovering Student-AI Interaction Patterns in Academic Writing through Epistemic Network Analysis

As Generative AI (GenAI) becomes integral to education, fostering GenAI literacy is critical. However, current assessments largely rely on self-reported scales, lacking insights into how literacy manifests in actual learning processes. This study leverages Learning Analytics (LA) to bridge this gap. We collected interaction logs from 162 university students engaged in a GenAI-assisted abstract writing task. Using Epistemic Network Analysis (ENA), we modeled and compared the questioning strategies of students with varying GenAI literacy levels. Preliminary results reveal distinct interaction signatures: high-literacy students engage in iterative refinement and strategic questioning, while low-literacy students rely on direct generation commands. This work contributes to the workshop by demonstrating how process data can characterize GenAI literacy, paving the way for data-driven literacy assessment and real-time interventions.

cs.CY↗

arXiv2026

From 50% to Mastery in 3 Days: A Low-Resource SOP for Localizing Graduate-Level AI Tutors via Shadow-RAG

Deploying high-fidelity AI tutors in schools is often blocked by the Resource Curse -- the need for expensive cloud GPUs and massive data engineering. In this practitioner report, we present a replicable Standard Operating Procedure that breaks this barrier. Using a Vision-Language Model data cleaning strategy and a novel Shadow-RAG architecture, we localized a graduate-level Applied Mathematics tutor using only 3 person-days of non-expert labor and open-weights 32B models deployable on a single consumer-grade GPU. Our pilot study on a full graduate-level final exam reveals a striking emergence phenomenon: while both zero-shot baselines and standard retrieval stagnate around 50-60% accuracy across model generations, the Shadow Agent, which provides structured reasoning guidance, triggers a massive capability surge in newer 32B models, boosting performance from 74% (Naive RAG) to mastery level (90%). In contrast, older models see only modest gains (~10%). This suggests that such guidance is the key to unlocking the latent power of modern small language models. This work offers a cost-effective, scientifically grounded blueprint for ubiquitous AI education.

cs.AI↗

arXiv2025

Can theory-driven learning analytics dashboard enhance human-AI collaboration in writing learning? Insights from an empirical experiment

The integration of Generative AI (GenAI) into education has raised concerns about over-reliance and superficial learning, particularly in writing tasks in higher education. This study explores whether a theory-driven learning analytics dashboard (LAD) can enhance human-AI collaboration in the academic writing task by improving writing knowledge gains, fostering self-regulated learning (SRL) skills and building different human-AI dialogue characteristics. Grounded in Zimmerman's SRL framework, the LAD provided real-time feedback on learners' goal-setting, writing processes and reflection, while monitoring the quality of learner-AI interactions. A quasi-experiment was conducted involving 52 postgraduate students divided into an experimental group (EG) using the LAD to a control group (CG) without it in a human-AI collaborative writing task. Pre- and post- knowledge tests, questionnaires measuring SRL and cognitive load, and students' dialogue data with GenAI were collected and analyzed. Results showed that the EG achieved significantly higher writing knowledge gains and improved SRL skills, particularly in self-efficacy and cognitive strategies. However, the EG also reported increased test anxiety and cognitive load, possibly due to heightened metacognitive awareness. Epistemic Network Analysis revealed that the EG engaged in more reflective, evaluative interactions with GenAI, while the CG focused on more transactional and information-seeking exchanges. These findings contribute to the growing body of literature on the educational use of GenAI and highlight the importance of designing interventions that complement GenAI tools, ensuring that technology enhances rather than undermines the learning process.

cs.HC↗

arXiv2008

The Generation of Textual Entailment with NLML in an Intelligent Dialogue system for Language Learning CSIEC

This research report introduces the generation of textual entailment within the project CSIEC (Computer Simulation in Educational Communication), an interactive web-based human-computer dialogue system with natural language for English instruction. The generation of textual entailment (GTE) is critical to the further improvement of CSIEC project. Up to now we have found few literatures related with GTE. Simulating the process that a human being learns English as a foreign language we explore our naive approach to tackle the GTE problem and its algorithm within the framework of CSIEC, i.e. rule annotation in NLML, pattern recognition (matching), and entailment transformation. The time and space complexity of our algorithm is tested with some entailment examples. Further works include the rules annotation based on the English textbooks and a GUI interface for normal users to edit the entailment rules.

cs.CL↗

arXiv2006

NLOMJ--Natural Language Object Model in Java

In this paper we present NLOMJ--a natural language object model in Java with English as the experiment language. This modal describes the grammar elements of any permissible expression in a natural language and their complicated relations with each other with the concept "Object" in OOP(Object Oriented Programming). Directly mapped to the syntax and semantics of the natural language, it can be used in information retrieval as a linguistic method. Around the UML diagram of the NLOMJ the important classes(Sentence, Clause and Phrase) and their sub classes are introduced and their syntactic and semantic meanings are explained.

cs.CL↗

arXiv2006

Improving the CSIEC Project and Adapting It to the English Teaching and Learning in China

In this paper after short review of the CSIEC project initialized by us in 2003 we present the continuing development and improvement of the CSIEC project in details, including the design of five new Microsoft agent characters representing different virtual chatting partners and the limitation of simulated dialogs in specific practical scenarios like graduate job application interview, then briefly analyze the actual conditions and features of its application field: web-based English education in China. Finally we introduce our efforts to adapt this system to the requirements of English teaching and learning in China and point out the work next to do.

cs.CY↗

arXiv2004

NLML--a Markup Language to Describe the Unlimited English Grammar

In this paper we present NLML (Natural Language Markup Language), a markup language to describe the syntactic and semantic structure of any grammatically correct English expression. At first the related works are analyzed to demonstrate the necessity of the NLML: simple form, easy management and direct storage. Then the description of the English grammar with NLML is introduced in details in three levels: sentences (with different complexities, voices, moods, and tenses), clause (relative clause and noun clause) and phrase (noun phrase, verb phrase, prepositional phrase, adjective phrase, adverb phrase and predicate phrase). At last the application fields of the NLML in NLP are shown with two typical examples: NLOJM (Natural Language Object Modal in Java) and NLDB (Natural Language Database).

cs.CL↗

arXiv2003

CSIEC (Computer Simulator in Educational Communication): An Intelligent Web-Based Teaching System for Foreign Language Learning

In this paper we present an innovative intelligent web-based computer-aided instruction system for foreign language learning: CSIEC (Computer Simulator in Educational Communication). This system can not only grammatically understand the sentences in English given from the users via Internet, but also reasonably and individually speak with the users. At first the related works in this research field are analyzed. Then we introduce the system goals and the system framework, i.e., the natural language understanding mechanism (NLML, NLOMJ and NLDB) and the communicational response (CR). Finally we give the syntactic and semantic content of this instruction system, i.e. some important notations of English grammar used in it and their relations with the NLOMJ.

cs.CY↗

arXiv2003

The Study of the Application of a Keywords-based Chatbot System on the Teaching of Foreign Languages

This paper reports the findings of a study conducted on the application of an on-line human-computer dialog system with natural language (chatbot) on the teaching of foreign languages. A keywords-based human-computer dialog system makes it possible that the user could chat with the computer using a natural language, i.e. in English or in German to some extent. So an experiment has been made using this system online to work as a chat partner with the users learning the foreign languages. Dialogs between the users and the chatbot are collected. Findings indicate that the dialogs between the human and the computer are mostly very short because the user finds the responses from the computer are mostly repeated and irrelevant with the topics and context and the program does not understand the language at all. With analysis of the keywords or pattern-matching mechanism used in this chatbot it can be concluded that this kind of system can not work as a teaching assistant program in foreign language learning.

cs.CY↗