Tutorial on NeuroSymbolic AI applied to NLP Material from the AAAI 2025 tutorial

Large Language Models are transforming natural language processing tasks in multiple domains in many ways. Despite their capabilities, their real-world adoption is often limited by issues like the lack of transparency, inadequate understanding of domain protocols, and subpar precision. 

Manas Gaur, Ed Raff, and Ali Mohammadi were part of the team that organized and presented a half-day tutorial at the 2025 AAAI Conference last month covering the concept of Neurosymbolic AI and how it can be applied to LLMs to help solve key challenges in NLP tasks like explainability, grounding, and instructability.

You can see their slides and other material here.

UMBC Center for AI ]]> Large Language Models are transforming natural language processing tasks in multiple domains in many ways. Despite their capabilities, their real-world adoption is often limited by issues like the... https://nesy-egi.github.io/ https://my3.my.umbc.edu/api/v0/pixel/news/148186/guest@my.umbc.edu/2c3ececc48c719a462b3d72dabdc0413/api/pixel ai llm nlp tutorial UMBC AI https://my3.my.umbc.edu/groups/umbc-ai https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets2-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779 https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779 UMBC AI 0 0 true Fri, 21 Mar 2025 10:18:25 -0400 Fri, 21 Mar 2025 10:41:51 -0400 UMBC adds New AI-Powered Search Bar to myUMBC Students can get personalized answers to searches

UMBC's Department of Information Technology (DoIT) has been exploring how new generative artificial intelligence systems can make the myUMBC  platform better for students, faculty, and staff, all while ensuring security and privacy. MyUMBC is a web portal that provides access to services and resources for the UMBC community of faculty, staff and students.

The search system on MyUMBC now uses an AI model to  make it easier and quicker for students to find what they need with AI. This helps provide fast, accurate answers to common student questions.

A key focus is helping students access important personal information—like grades, billing statements, and Retriever Card balances—right from the search bar. This means students can find what they need quickly, without having to dig through the system, while knowing their data is protected.

DoIT is looking at how AI can further improve the myUMBC experience, from academic support to campus life to create a more efficient and personalized platform. 

Currently answers are focused on student-related questions and scenarios with supporting questions from faculty and staff still in development. Students are advised to verify any information before they take action. If you identify any mistakes, please let the developers know using the “Was this useful” feature at the bottom of each answer.

UMBC Center for AI ]]> UMBC's Department of Information Technology (DoIT) has been exploring how new generative artificial intelligence systems can make the myUMBC  platform better for students, faculty, and staff, all... https://my3.my.umbc.edu/groups/doit/posts/147188 https://my3.my.umbc.edu/api/v0/pixel/news/147265/guest@my.umbc.edu/6c113e2e2d2b4f5831ec6898b593d577/api/pixel ai help llm myumbc search UMBC AI https://my3.my.umbc.edu/groups/umbc-ai https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets2-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779 https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779 UMBC DoIT 0 0 true Tue, 11 Feb 2025 18:57:14 -0500 Tue, 11 Feb 2025 21:31:33 -0500 Talk: From Social Media Mining to Generative AI: Asking and Solving Challenging Problems Huan Liu, ASU, 12-1pm ET Wed. Feb 5, ITE 459 & online

UMBC Distinguished Speaker

From Social Media Mining to Generative AI: Asking and Solving Challenging Problems

Huan Liu, Arizona State University

Wednesday, Feb. 5, 12-1pm EST, ITE 459, UMBC & online

In this talk, we will present emerging opportunities in AI and Big Data, through the lens of social media. Generative AI, in particular, Large Language Models (LLMs), has added new challenges. We use examples to illustrate (1) fundamental problems associated with multi-modal data like social media, challenging common practice and existential understanding in machine learning and data mining, (2) how we embrace the power of LLMs to solve perplexing problems, and (3) developing novel algorithms for responsible LLMs. Seeking interdisciplinary collaborations, we contemplate the promising future of data science and data mining in the rapid development of AI.

Dr. Huan Liu is a Regents Professor and Ira A. Fulton professor of Computer Science and Engineering at Arizona State University. He is the recipient of the ACM SIGKDD 2022 Innovation Award for his outstanding contributions to the foundation, principles, and applications of social media mining and feature selection for data Mining. He co-authored the textbook, Social Media Mining: An Introduction, by Cambridge University Press. He is Editor in Chief of ACM TIST, Founding Field Chief Editor of Frontiers in Big Data, its Specialty Chief Editor of Data Mining and Management, and a founding organizer of the International Conference Series on Social Computing, Behavioral-Cultural Modeling, and Prediction. He is a Fellow of ACM, AAAI, AAAS, and IEEE.
UMBC Center for AI ]]> UMBC Distinguished Speaker From Social Media Mining to Generative AI: Asking and Solving Challenging Problems Huan Liu, Arizona State University Wednesday, Feb. 5, 12-1pm EST, ITE 459, UMBC... https://informationsystems.umbc.edu/home/calendar/events/ https://my3.my.umbc.edu/api/v0/pixel/news/146981/guest@my.umbc.edu/9ec839ddb357706b493328d2406bf9ac/api/pixel ai llm talk UMBC AI https://my3.my.umbc.edu/groups/umbc-ai https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets2-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779 https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779 UMBC Department of Information Systems 0 0 true Mon, 03 Feb 2025 13:18:40 -0500 Mon, 03 Feb 2025 13:24:29 -0500 Talk: Do LLMs Exhibit Cybersecurity Misconceptions? 1/31 online Evaluation of LLMs on Cybersecurity Concept Inventories

Do LLMs Show Cybersecurity Misconceptions?

Evaluation of LLMs Performance on Cybersecurity Concept Inventories
Shan Huang, UIUC
Joint work with Jeffrey Herman and Alan Sherman, et al.
12:00–1pm ET Friday, Jan. 31, 2025, online 

We evaluated the performance of five LLMs (Llama a, GPT-3.5-turbo, GPT-4, GPT-4O, and GPT-O1) on two cybersecurity concept inventories: Cybersecurity Concept Inventory (CCI) and Cybersecurity Curriculum Assessment (CCA). Using a zero-shot setting to minimize external influencing factors, we compared the performance of these LLMs with that of students previously studied, and we conducted a qualitative analysis of GPT-O1's output to examine if it exhibits misconceptions. Quantitative analysis reveals that, for the CCI and CCA, GPT-O1 significantly outperformed other models and students, correctly answering 92% of CCI and 72% of CCA test items. These results indicate GPT-O1’s strong proficiency in foundational topics (CCI) but reveal its limitations in addressing these concepts in more technically advanced scenarios (CCA). Qualitative analysis of GPT-O1’s reasoning patterns uncovered instances of insightful reasoning but also highlighted ways in which GPT-O1's answers reflect persistent student mistakes, such as biases, overgeneralizations, and logical inconsistencies. This work highlights the significant potential of GPT-O1 as a tool for introductory cybersecurity education in its ability to provide detailed explanations and structured reasoning for novice learners.

Shan Huang is a Ph.D. candidate in Computer Science at the University of Illinois Urbana-Champaign. She is broadly interested in how educational games can improve student learning. Current work includes improving student learning in cybersecurity with educational games and accessing student knowledge of cybersecurity concepts. Shan is also involved in various educational data mining projects.

UMBC Center for AI ]]> Do LLMs Show Cybersecurity Misconceptions? Evaluation of LLMs Performance on Cybersecurity Concept Inventories Shan Huang, UIUC Joint work with Jeffrey Herman and Alan Sherman, et al.... https://my3.my.umbc.edu/api/v0/pixel/news/146793/guest@my.umbc.edu/1ca42e886baeb4a9edbebb1da8e736fc/api/pixel ai cca cci cybersecurity llm UMBC AI https://my3.my.umbc.edu/groups/umbc-ai https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets2-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779 https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779 UMBC Cyber Defense Lab https://assets1-my.umbc.edu/system/shared/thumbnails/news/000/146/793/f8af6870dd1080f5b47500ad019d548b/xxlarge.jpg?1738081136 https://assets2-my.umbc.edu/system/shared/thumbnails/news/000/146/793/f8af6870dd1080f5b47500ad019d548b/xlarge.jpg?1738081136 https://assets2-my.umbc.edu/system/shared/thumbnails/news/000/146/793/f8af6870dd1080f5b47500ad019d548b/large.jpg?1738081136 https://assets4-my.umbc.edu/system/shared/thumbnails/news/000/146/793/f8af6870dd1080f5b47500ad019d548b/medium.jpg?1738081136 https://assets4-my.umbc.edu/system/shared/thumbnails/news/000/146/793/f8af6870dd1080f5b47500ad019d548b/small.jpg?1738081136 https://assets4-my.umbc.edu/system/shared/thumbnails/news/000/146/793/f8af6870dd1080f5b47500ad019d548b/xsmall.jpg?1738081136 https://assets2-my.umbc.edu/system/shared/thumbnails/news/000/146/793/f8af6870dd1080f5b47500ad019d548b/xxsmall.jpg?1738081136 0 0 true Tue, 28 Jan 2025 11:53:43 -0500 Benchmarks that have been killed by LLM based systems

Killed by LLM is a project that documents public AI benchmarks that LLM-based AI systems have largely solved since 2018.  Getting killed means that a benchmark no longer measures the frontier of AI technology as a challenge asking "Can AI do X?", but might still be a useful tool. Links to papers documenting fallen benchmarks are provided.

The project is on GitHub, and other people are invited to contribute new benchmarks that have been overcome.

UMBC Center for AI ]]> Killed by LLM is a project that documents public AI benchmarks that LLM-based AI systems have largely solved since 2018.  Getting killed means that a benchmark no longer measures the frontier of... https://r0bk.github.io/killedbyllm/ https://my3.my.umbc.edu/api/v0/pixel/news/146462/guest@my.umbc.edu/ca6832dc7212f2aa8d1e3e650c26f51c/api/pixel ai benchmark llm UMBC AI https://my3.my.umbc.edu/groups/umbc-ai https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets2-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779 https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779 UMBC AI 0 0 true Tue, 07 Jan 2025 09:18:50 -0500 Tue, 07 Jan 2025 09:20:46 -0500 Google's five-day Generative AI intensive course Now a free, self-paced learning program at Kaggle Google's five day Generative AI Intensive Course is now available as a free, self-paced learning program on Kaggle for anyone interested in learning about the fundamental technologies and techniques behind the latest Generative AI technology. Get more information here.

Here's what the course covers
  • Day 1: Foundational Models & Prompt Engineering - Explore the evolution of LLMs, from transformers to techniques like fine-tuning and inference acceleration. Get trained with the art of prompt engineering for optimal LLM interaction.

  • Day 2: Embeddings and Vector Stores/Databases - Learn about the conceptual underpinning of embeddings and vector databases, including embedding methods, vector search algorithms, and real-world applications with LLMs, as well as their tradeoffs.

  • Day 3: Generative AI Agents - Learn to build sophisticated AI agents by understanding their core components and the iterative development process.

  • Day 4: Domain-Specific LLMs - Delve into the creation and application of specialized LLMs like SecLM and Med-PaLM, with insights from the researchers who built them.

  • Day 5: MLOps for Generative AI - Discover how to adapt MLOps practices for Generative AI and leverage Vertex AI's tools for foundation models and generative AI applications.

UMBC Center for AI
]]> Google's five day Generative AI Intensive Course is now available as a free, self-paced learning program on Kaggle for anyone interested in learning about the fundamental technologies and... https://www.kaggle.com/learn-guide/5-day-genai https://my3.my.umbc.edu/api/v0/pixel/news/146371/guest@my.umbc.edu/ed8e4ac27657b1390342d00ca95a0073/api/pixel agents ai genai kaggle llm UMBC AI https://my3.my.umbc.edu/groups/umbc-ai https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets2-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779 https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779 UMBC AI https://assets4-my.umbc.edu/system/shared/thumbnails/news/000/146/371/3279e2c68aaf86bef1ca5a2607cca81e/xxlarge.jpg?1734559613 https://assets4-my.umbc.edu/system/shared/thumbnails/news/000/146/371/3279e2c68aaf86bef1ca5a2607cca81e/xlarge.jpg?1734559613 https://assets3-my.umbc.edu/system/shared/thumbnails/news/000/146/371/3279e2c68aaf86bef1ca5a2607cca81e/large.jpg?1734559613 https://assets3-my.umbc.edu/system/shared/thumbnails/news/000/146/371/3279e2c68aaf86bef1ca5a2607cca81e/medium.jpg?1734559613 https://assets3-my.umbc.edu/system/shared/thumbnails/news/000/146/371/3279e2c68aaf86bef1ca5a2607cca81e/small.jpg?1734559613 https://assets4-my.umbc.edu/system/shared/thumbnails/news/000/146/371/3279e2c68aaf86bef1ca5a2607cca81e/xsmall.jpg?1734559613 https://assets2-my.umbc.edu/system/shared/thumbnails/news/000/146/371/3279e2c68aaf86bef1ca5a2607cca81e/xxsmall.jpg?1734559613 3 1 true Wed, 18 Dec 2024 17:32:37 -0500 CodeBot '25: Can We Trust AI-Generated Code? 2/25-26 Workshop Feb. 25-26, 2025 in Columbia, MD and online

Can We Trust AI-Generated Code?

Workshop sponsored by UMBC & Army Research Laboratory
Feb. 25-26, 2025 UMBC Training Centers, Columbia, MD & online

position paper deadline extended to 1/20/2025
The era of generative AI is upon us, and chatbots such as chatGPT are being used by programmers at all levels of experience to produce code.  Some generative AI systems, such as Gemini Code Assist, specialize in code generation.  Unfortunately, AI-generated code often contains errors in the form of functionality that fails to meet specifications or vulnerabilities that can be exploited by hackers.  People have been working on program verification and secure coding for sixty years, but even so, the skill needed to find such errors is possessed by only a fraction of software engineers, and these skills are not being passed on to student programmers as they should be.

The goal of this FREE workshop is to gather and produce actionable ideas and suggestions that may be of use to the IT profession.  The workshop will consist of invited speakers, panels, and open discussion. 

We invite would-be participants to submit short position papers offering comments, observations, experiences, and suggestions that pertain to any or all of the following workshop themes:
  1. What is or could be done to make AI-generated code more trustworthy, from the perspective of functionality and/or cybersecurity?
  2. How can we do better at instilling the ideas and tools of secure development into the software profession?
  3. Being able to produce quality code, with or without the aid of AI, seems to be related to system skills in general. How can we do better at giving students these skills before (or as) they enter the workplace?
Position papers should limited to three pages and submitted according to this template.  Submit your position paper via email to codebot25@umbc.edu after registering for the workshop.

The organizing committee will select several papers for live presentation at the workshop. Selection will be based on relevance to the workshop themes, technical merit, and perceived interest to the audience.  Position papers that are mere marketing pieces will not be considered, but descriptions of hardware and software solutions tying into the themes described above are welcome. Limited travel support may be available for non-local speakers. Position papers and summaries of the discussions that follow will make up the core of the workshop report.

UMBC students, both graduate or undergraduate, are welcome to submit position papers that describe their own personal experience and observations with AI-generated code in their own words.  Students may include their resumes with position papers if they wish to have their work/resume circulated to other attendees.  Domestic and international students are welcome to participate in this workshop.

Important Dates:
  Position paper submission deadline: January 20, 2025
   P̶o̶s̶i̶t̶i̶o̶n̶ p̶a̶p̶e̶r̶ s̶u̶b̶m̶i̶s̶s̶i̶o̶n̶ d̶e̶a̶d̶l̶i̶n̶e̶:̶ J̶a̶n̶u̶a̶r̶y̶ 7̶, 2̶0̶2̶5̶
  Notice of acceptance: January 31, 2025
  Registration deadline: February 18, 2025
    (no registration fee, but space is limited)
  Workshop dates: February 25-26, 2025

The workshop will take place at UMBC Training Centers, 6996 Columbia Gateway Dr #100, Columbia, MD 21046

REGISTER @ https://forms.gle/CipmPbbBVBLfHc728

In-person space is limited, so register early! Based on RSVPs received, the organizing committee reserves the right to be selective in whom it selects to join the in-person meeting.

Instructions for virtual participation will be made available prior to the workshop.

Organizing Committee:
  Prajna Bhandary, UMBC
  Mike De Lucia, Army Research Laboratory
  Richard Forno, UMBC
  Lindsay Gaughan, UMBC Training Centers
  Cynthia Matuszek, UMBC
  Charles Nicholas, UMBC
  Steve Simske, Colorado State University
  Larry Wagoner, Dept. of Defense
  Linda Kidder Yarlott, UMBC
  Paul Yu, Army Research Laboratory

Questions? Send email to codebot25@umbc.edu
UMBC Center for AI ]]> Can We Trust AI-Generated Code? Workshop sponsored by UMBC & Army Research Laboratory Feb. 25-26, 2025 UMBC Training Centers, Columbia, MD & online position paper deadline extended... https://my3.my.umbc.edu/api/v0/pixel/news/146132/guest@my.umbc.edu/b17c8edd1328de0083d7b2c24898a735/api/pixel ai code genai llm programming workshop UMBC AI https://my3.my.umbc.edu/groups/umbc-ai https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets2-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779 https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779 UMBC and Army Research Laboratory https://assets4-my.umbc.edu/system/shared/thumbnails/news/000/146/132/4fef019b80ee408244a74c360da53f18/xxlarge.jpg?1733760093 https://assets1-my.umbc.edu/system/shared/thumbnails/news/000/146/132/4fef019b80ee408244a74c360da53f18/xlarge.jpg?1733760093 https://assets2-my.umbc.edu/system/shared/thumbnails/news/000/146/132/4fef019b80ee408244a74c360da53f18/large.jpg?1733760093 https://assets3-my.umbc.edu/system/shared/thumbnails/news/000/146/132/4fef019b80ee408244a74c360da53f18/medium.jpg?1733760093 https://assets3-my.umbc.edu/system/shared/thumbnails/news/000/146/132/4fef019b80ee408244a74c360da53f18/small.jpg?1733760093 https://assets2-my.umbc.edu/system/shared/thumbnails/news/000/146/132/4fef019b80ee408244a74c360da53f18/xsmall.jpg?1733760093 https://assets1-my.umbc.edu/system/shared/thumbnails/news/000/146/132/4fef019b80ee408244a74c360da53f18/xxsmall.jpg?1733760093 2 0 true Sat, 07 Dec 2024 09:36:27 -0500 Tue, 07 Jan 2025 16:58:41 -0500 Microsoft Webinar: Copilot Studio for Education, 11/21 Build a generative AI chatbot in minutes, 11/21, 11-12 EST

Microsoft’s Copilot Studio is a conversational AI platform that lets you create agents using natural language or a graphical interface that are based on the GPT-4 series of large language models. Using Copilot Studio, you can more easily design, test, and publish agents that suit your needs for internal or external scenarios across your university, department, or role. This one-hour webinar is focused on using it for education by faculty, staff, and students: 11-12pm EST, Thursday, November 21, 2024, online. Register here. 
UMBC Center for AI ]]> Microsoft’s Copilot Studio is a conversational AI platform that lets you create agents using natural language or a graphical interface that are based on the GPT-4 series of large language models.... https://my3.my.umbc.edu/groups/meec/posts/145617 https://my3.my.umbc.edu/api/v0/pixel/news/145682/guest@my.umbc.edu/ca6f3746a2f3b5ce178b4a2dc0df457b/api/pixel agents chatgpt copilot education genai llm microsoft studio UMBC AI https://my3.my.umbc.edu/groups/umbc-ai https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets2-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779 https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779 UMBC AI https://assets4-my.umbc.edu/system/shared/thumbnails/news/000/145/682/162e97af3429e0d41bf14fe7cfc6591f/xxlarge.jpg?1731801136 https://assets1-my.umbc.edu/system/shared/thumbnails/news/000/145/682/162e97af3429e0d41bf14fe7cfc6591f/xlarge.jpg?1731801136 https://assets3-my.umbc.edu/system/shared/thumbnails/news/000/145/682/162e97af3429e0d41bf14fe7cfc6591f/large.jpg?1731801136 https://assets2-my.umbc.edu/system/shared/thumbnails/news/000/145/682/162e97af3429e0d41bf14fe7cfc6591f/medium.jpg?1731801136 https://assets1-my.umbc.edu/system/shared/thumbnails/news/000/145/682/162e97af3429e0d41bf14fe7cfc6591f/small.jpg?1731801136 https://assets2-my.umbc.edu/system/shared/thumbnails/news/000/145/682/162e97af3429e0d41bf14fe7cfc6591f/xsmall.jpg?1731801136 https://assets3-my.umbc.edu/system/shared/thumbnails/news/000/145/682/162e97af3429e0d41bf14fe7cfc6591f/xxsmall.jpg?1731801136 0 0 true Sat, 16 Nov 2024 18:58:40 -0500 Sat, 16 Nov 2024 21:45:56 -0500 talk: Confabulation: What Could LLM Hallucinations Do For Storytelling? 11/14 11:30-12:50 Thur. Nov. 14, 2024, Sondheim Hall 110 & online

Peiqi "Patrick" Sui will talk on Confabulation: What Could LLM Hallucinations Do For Storytelling?, 11:30am-12:50pm on Thursday, Nov. 14, 2024 in Sondheim Hall 110 at UMBC and online. 

Are hallucinations always bad? Most of NLP research presumes a normative stance that they are, but it overlooks the cognitive and communicative affordances of a type of particularly story-like hallucinations (which we'll call confabulations). Consider two general categories of LLM applications: using them as tools, or interacting with them as viable cultural agents. The two have very different training objectives in terms of the tradeoff between factuality and alignment with the human behavior of storytelling, and when it comes to ensuring the latter, LLMs that could effectively confabulate would be especially useful. For instance, confabulations could enable LLMs to perform speculative narration and address omissions in history resulting from social injustice, in the hope of enacting what literary theorist Saidiya Hartman calls "critical fabulation" at scale, and giving interactive storytelling a wider social impact.

Patrick Sui is a second-year PhD student in English at McGill University, advised by Richard Jean So. He mainly works in digital humanities and cultural analytics, and spends most of his time thinking about how literary studies could uniquely contribute to AI research about language. His current research topics include benchmarks for close reading & interpretive reasoning, modeling close reading behaviors with information theory, knowledge-grounded style transfer for co-creative systems, AI literacy & writing pedagogy, and all kinds of computational literary theory.

The talk is part of the UMBC Language Technology Seminar Series.

UMBC Center for AI ]]> Peiqi "Patrick" Sui will talk on Confabulation: What Could LLM Hallucinations Do For Storytelling?, 11:30am-12:50pm on Thursday, Nov. 14, 2024 in Sondheim Hall 110 at UMBC and online.  Are... https://laramartin.net/LaTeSS https://my3.my.umbc.edu/api/v0/pixel/news/145547/guest@my.umbc.edu/4654d8b43ac207b29c7a91e8e6ca00b8/api/pixel ai lara-lab llm nlp storytelling UMBC AI https://my3.my.umbc.edu/groups/umbc-ai https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets2-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779 https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779 Language, Aid, and Representation AI Lab 0 0 true Mon, 11 Nov 2024 18:08:30 -0500 Mon, 11 Nov 2024 19:06:30 -0500 AI in Practice: How Faculty and Entrepreneurs Are Actually Using Generative AI 12-1 pm EST, Wednesday, November 13, 2024, online
The next online session of the AI in Practice series will be  "How Faculty and Entrepreneurs Are Actually Using Generative AI: “Use Case” Lightning Round" on 12-1 pm EST, Wednesday, November 13, 2024.

Do you wonder: How can I actually use AI in my life? In this fast-paced session five leading faculty members and entrepreneurs from UMB, UMBC, and JHU will share their most practical AI use cases, delivered in just five minutes each. You'll hear more than 15 examples of concrete ways you can use AI today. 

The presenters are John G Schumacher (UMBC), Mikhail B. Pevzner (UBALT), Carly Schnitzler (JHU), Paul Davidson (JHU), and  Henry Mortimer (UBALT).

Register here.

UMBC Center for AI ]]> The next online session of the AI in Practice series will be  "How Faculty and Entrepreneurs Are Actually Using Generative AI: “Use Case” Lightning Round" on 12-1 pm EST, Wednesday, November 13,... https://my3.my.umbc.edu/api/v0/pixel/news/145338/guest@my.umbc.edu/a937dd99c5918fa033d0fdda823332ad/api/pixel ai genai llm teaching university use-case UMBC AI https://my3.my.umbc.edu/groups/umbc-ai https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets2-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/original.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xlarge.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/large.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/medium.png?1691095779 https://assets3-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/small.png?1691095779 https://assets4-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xsmall.png?1691095779 https://assets1-my.umbc.edu/system/shared/avatars/groups/000/002/081/cfb27ebe008c2636486089a759ea5c36/xxsmall.png?1691095779 UMBC AI Center 0 0 true Mon, 04 Nov 2024 18:18:05 -0500 Mon, 04 Nov 2024 18:19:15 -0500