AI Discovery Zone @ EdUHK Library's Research Support

Showing 10 of 12 Results

Discover Qwen3-Max – A Powerful AI Resource for College Students
10/23/2025
Isaac Tai
No Subjects

We’re excited to share news about Qwen3-Max, the latest AI model from the Qwen3 series, designed to support your academic and creative endeavors. With over 1 trillion parameters and training on 36 trillion tokens, Qwen3-Max is a remarkable tool for tackling coursework, coding projects, and complex problem-solving.

What is Qwen3-Max?

  • Qwen3-Max-Instruct, the flagship model, ranks third globally on the LMArena leaderboard, surpassing many leading AI models. It excels in:
  • Coding: With a score of 69.6 on Verified SWE-Bench, it's an excellent tool for computer science students that are solving programming problems.
  • Agent Capabilities: With a 74.8 score on Tau2-Bench, it can facilitate operations like automation and integration of tools, better suited for project development.
  • Reasoning: The new-generation Qwen3-Max-Thinking model has achieved top 100% on challenging math benchmarks like AIME 25 and HMMT, promising to be a helpful tool for mathematics-heavy disciplines.

Why It Matters for You

Qwen3-Max can help your studies in a host of ways, from code completion to explaining obtuse concepts and creating research or project ideas. From debugging code, solving equations, to researching new material, this AI model is the solid support you need to do it correctly.

A Peek Behind the Tech

Qwen3-Max has a Mixture of Experts (MoE) architecture and ChunkFlow, enabling it to process vast amounts of information like contexts of 1 million tokens efficiently. It is ideal for processing long texts or data sets, the best buddy of a research-intensive project.

How to Discover Qwen3-Max

  • Try Qwen Chat: Use Qwen3-Max-Instruct directly in Qwen Chat to ask a question or ask for your task.
  • Use the API: Available via Alibaba Cloud Model Studio, the API allows you to integrate Qwen3-Max into your applications. Sign up for an Alibaba Cloud account and begin building.
  • Stay Tuned: Qwen3-Max-Thinking, committed to high-level thinking, is in development but will soon be available for public use.
Which AI Model Wins? Exploring the LMArena Leaderboard
10/02/2025
Isaac Tai
No Subjects

The LMArena Leaderboard is a cutting-edge benchmarking platform for evaluating large language models (LLMs), designed to provide rigorous, data-driven rankings based on model performance in diverse text-based tasks. It is particularly valuable for university students and academic researchers seeking empirical foundations for selecting AI models in research and educational settings.

 

LMArena originated as an academic project at the University of California, Berkeley, developed to systematically measure the capabilities of AI models using reproducible, user-driven evaluation workflows. Utilizing human preference judgments and controlled evaluation methodologies—including the pioneering “Style Control” protocol, which disentangles superficial presentation features from substantive reasoning—the leaderboard sustains high methodological standards and is increasingly cited in scholarly literature.

 

The platform hosts side-by-side comparisons of hundreds of text models, leveraging millions of user votes to compute statistical scores associated with confidence intervals. These measures provide transparency and enable robust model selection for academic inquiry, ranging from computational linguistics and digital humanities to applied AI research.

 

 

 

ResearchRabbit: Free Literature Search for Academics and Students
08/14/2025
Research Related
decorative-image

Academic research often begins with a daunting question: “Where do I start?” For both university staff and students, navigating the vast landscape of academic papers can feel overwhelming—especially when working on literature reviews, essays, dissertations, or exploring new topics. Enter ResearchRabbit: a modern, AI-powered literature mapping tool designed to make academic discovery faster, smarter, and more insightful.

What is ResearchRabbit?

ResearchRabbit is a free online platform that helps users visualize, discover, and curate research publications through an innovative, citation-based mapping interface. Rather than scrolling through endless database results, you can now start with just one or two seed papers and let ResearchRabbit uncover connected articles, authors, and trends in your chosen field

Key Features for Academic Staff and Students

 

  • Accessible & Free
    ResearchRabbit runs entirely in your browser—no software installation required—and is free for researchers, students, and academics alike.

  • Dynamic Literature Maps
    ResearchRabbit creates stunning, interactive visual maps that show relationships between papers, authors, and citations. This bird’s-eye view helps users see the “big picture” of a research area, identify influential work, and spot potential gaps in the literature.

  • Citation Trails and Author Networks
    Explore citation relationships—see what papers influenced your seed articles (backward citations), follow who cited them (forward citations), or find similar works. You can also map out author collaborations, which is especially useful for understanding expert networks in a discipline.

  • Curated Collections
    Organize your discoveries into collections. These can be shared with colleagues or students, making collaboration and group projects a breeze.

  • Personalized, Smart Recommendations
    The more papers you add to your collection, the better ResearchRabbit becomes at recommending other relevant work. It learns your interests and keeps you up-to-date by alerting you to new, related publications.

How Can University Staff and Students Benefit?

  • For Researchers & Academics:
    Quickly map the landscape of a new research topic, uncover influential publications, and organize reading lists for course or lab groups.

  • For Students:
    Simplify the literature review process for essays, theses, or dissertations. No more fear of missing out on key papers—ResearchRabbit’s smart mapping and recommendations have you covered.jcu+1

  • For Collaborative Projects:
    Share collections, annotate papers, and collaboratively build a group bibliography. Perfect for lab groups, courses, or supervision meetings.

Getting Started

  1. Sign up at researchrabbit.ai (free account required).

  2. Create a collection and add one or more seed papers (by uploading a file, pasting in a DOI, or searching for a title).

  3. Explore the dynamic maps, expand your collection, and organize key findings.

  4. Share with peers, annotate, and keep building your personalized research landscape.

Pro Tips

  • Use ResearchRabbit alongside your university’s academic databases for the most robust literature mapping.

  • Take advantage of visualizations to present literature overviews in classes, seminars, or project meetings.

  • Encourage students to organize their thesis or dissertation sources with ResearchRabbit for better research management.

Conclusion:
ResearchRabbit is transforming how university academics and students discover and interact with the scholarly literature. Its unique, visual, and collaborative approach to literature mapping makes it an indispensable platform for anyone serious about research in the digital age.jcu+2

Generative AI in Library Databases
07/28/2025
No Subjects

Many library databases and subscription services now integrate AI-powered tools to improve user experience, content discovery, and accessibility. Below is a list of subscribed library resources that feature AI-driven research assistant capabilities:

 

PlatformTool nameRemarks
EBSCOhostAI Insights
FactivaSmart Summary
JSTORAI Research Tool
  • Require to login to personal account when accessing via EZProxy
  • Can be accessed when viewing both journal articles and book chapters
ProQuestResearch Assistant
CNKI CNKI SmartOn trial until 31 October 2025
iSearchPrimo Research Assistant
  • Require to login to MyLibrary account
  • Libguide
Dow Jones Launches Factiva Smart Summary
07/08/2025
No Subjects

Factiva Smart Summary provides innovative ways to utilize Factiva content by prompting, summarizing, and highlighting the most relevant articles. Users can also create customized newsletters. A free-text prompt gives replies based on selected articles from a large number of sources, drawing from a multi-year archive As an AI summarization tool, its primary advantage lies in saving users time by reducing the need to read all articles from Factiva's curated content.  Learn more

Scite summer Bootcamp
06/24/2025
Research Related, Artificial Intelligence

Master AI for Research This Summer & Get Your AI for Research Certificate 

 

This bootcamp is organised by Scite.  Throughout the bootcamp, you'll receive emails from scite including:

  • Session reminders with Zoom links
  • Pre-session preparation materials
  • Practical exercises and resources
  • Tips for maximizing your AI research skills
  • Certificate completion updates

Get Your AI for Research Certificate

Remember: Attend any 3 out of 4 sessions (with one industry session mandatory) to earn your AI for Research Certificate.

 

Registration

 

 

CNKI launches AI Academic Assistant
06/18/2025
Research Related, Artificial Intelligence

CNKI has recently launched AI Academic Research Assistant, an advanced tool that leverages artificial intelligence technology to assist in scientific research. This new version is based on CNKI's vast academic resources and the intelligent technology of the HuaZhi large model, closely integrating AI large model technology, high-quality data, and research scenarios, aiming to enhance efficiency in key areas such as literature retrieval, reading, and academic writing. 

CNKI has provided a trial for the EdUHK current students and staff on the “CNKI AI” services till Oct 31 2025. The services have integrated with DeepSeek R1. Services included: 

• Chatbot grounded on CNKI contents

 • Research assistant based on single article / a collection of articles (up to 10) 

• Writing assistant 

You can test the services by visiting this URL within campus IPs: https://aismart.oversea.cnki.net/ 

You will also need to create a personal account to use the services. 

Though there is no limit on the number of accounts that can be created, each account has its own quota for various services:

 

EBSCO's Natural Language Search mode: No More Keywords to Discover Research
04/28/2025
Research Related
decorative-image

Highlight Summary

 

EBSCO now provides a Natural Language Search mode that uses LLMS to allow you to search using everyday language. It understands what you’re looking for, even if you ask in full sentences, and it delivers better results.

 

How Does Natural Language Search Work?

 

Natural Language Search (NLS) lets you search the way you naturally speak or write—no need for special keywords or complicated search rules. No need to use the complex keywords or Boolean operators, for example, you can ask the question "What is the best education for children?" instead of using (education OR schooling) AND (child* OR kid* OR student* OR pupil*) AND (best OR optimal OR effective) AND ("academic achievement" OR outcomes OR “learning results”).

 

Here is the comparison table of Traditional Search vs. Natural Language Search:

Traditional Search

Natural Language Search

Requires keywordsAccepts complete questions
Needs Boolean operatorsUnderstands natural phrasing
Often needs multiple attemptsFrequently succeeds on first try

 

How to Use Natural Language Search Mode?

 

STEP 1: Go to “Advanced Search Mode” from the basic search.

STEP 2: Under “Search options”, you can select “Natural language” to turn on this mode.

STEP 3:  To turn on NLS mode immediately, simply toggle the Natural Language switch in basic search.

Step 4:  Now let's test NLS mode with our sample question: “What is the best education for children?” Observe how NLS generates 810,595 comprehensive results while the traditional search generates a limited 250 records.

You'll notice that the NLS mode retrieves relevant results containing conceptually related terms, such as “teaching”, “effective”, and “students”—even though these exact words weren't included in our original search query. This demonstrates a key advantage of Natural Language Search: unlike traditional keyword-based systems, NLS leverages Large Language Models (LLMs) to interpret the semantic meaning behind your question, eliminating the need for exact keyword matching.

Recommendations from the Library:

To get the most out of EBSCO's search tools, the following strategies for combining NLS and traditional search mode are:

  •  Begin with NLS to explore topics broadly using conversational queries
  • Switch to traditional search to refine results using precise keywords, Boolean operators, or field tags
Explore Scite Assistant’s New AI-Powered Tables
03/18/2025
Research Related, Artificial Intelligence

The Library has already subscribed to Scite, a powerful AI research tool designed to elevate your research experience. 

Our subject guide, “AI Tools for Your Research: Scite” explains its features and provides instructions for getting started. Recently Scite has launched a new feature, Tables in Scite Assistant, a major advancement that enables researchers to extract, organize and analyze data from scientific literature. 

How to Use AI Tables?
Scite's AI Tables do more than just summarize papers—they help you extract specific data points, methodologies, and outcomes directly from scientific articles.

Step 1: Go to Scite Assistant and select “Use Table Mode” for the new Table function.

 

Step 2: Click “Add Column” and type “name” and “instructions” for the new column. You can choose the length of the answers, from short to long.

 

Step 3: Continue creating new columns, such as “Methodology,” “Key Findings,” and others, to organize and analyze your data effectively.

In addition, you can export all references with all columns in various formats, such as CSV, ris and BibTeX.

 

New Improvements to Scite Assistant

OpenAI o3 mini + Reasoning

A new AI model, OpenAI o3 mini, now integrates advanced reasoning capabilities and is being utilized by Scite. Scite enhances its platform by combining its own datasets and access to scholarly content with powerful AI models, offering researchers tools for analysis and discovery.

What is “Reasoning”?

Reasoning Models: These are advanced AI systems that go beyond simple pattern recognition (which is what most standard AI models do). Instead, they are designed to:

  1. Think through problems internally before answering.
  2. Consider multiple approaches to solving a question.
  3. Evaluate the accuracy of different possible answers. 
  4. Plan structured and coherent responses.
  5. Solve multi-step problems methodically.
What is Covidence? - A Smart Way to Manage Your Systematic Reviews
03/06/2025
Research Related, Artificial Intelligence

Covidence = “Collaboration” + “Evidence”, is a powerful web-based platform designed to simplify and accelerate the systematic review process. Researchers and students may feel the systematic review workload is overwhelming, from screening thousands of articles to extracting data and resolving conflicts. 

 

What can Covidence do?

Covidence can support key stages of the review process, including:

Get Started with Covidence

While the library does not currently have a subscription to Covidence, a trial has been established for all EdUHK members until April 15, 2025. Trial accounts can only be created by invitation. If you are interested in trying it out, please inform us at myhyiu@eduhk.hk, and the library will send you an invitation as below:

Invitation

Note: When you fill in the required information to complete the registration, remember to use your EdUHK email.

 

Training Resources from Covidence

Covidence has its own YouTube channel with video tutorials to to guide you through the main features of the system. 

 

Useful Resources from Covidence

Field is required.