Skip to main content

Artificial Intelligence & Machine Learning Research Area

College of Information Science faculty are leaders in artificial intelligence and machine learning research, including AI, causal inference, data mining, deep learning, large language models, natural language processing and understanding, probabilistic modeling, social network analysis, and statistics and statistical learning.

View Faculty

View Select Current & Recent Research

Faculty

Cristian Román-Palacios

Cristian Román

Assistant Professor
Coordinator and Advisor for MSDS and MSIS
  • Phylogenetics and biodiversity drivers
  • Paleoclimatic reconstructions and climate change
  • Applied data mining and machine learning
cromanpa@arizona.edu

Select Current & Recent Research

Current and recent funded faculty research in this area includes but is not limited to the following projects:

HAILMEIER-C: Harnessing Artificial Intelligence and Language Modeling for Enhancing Innovation and Evaluating Research Claims
PI: Peter Jansen (The University of Arizona)
Funding: University of Pennsylvania, Defense Advanced Research Projects Agency, $949,484
Project Dates: September 1, 2025 – July 31, 2027
Publications:
"Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Science,” Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025
“CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents,” Submitted November 2025
Website: www.darpa.mil/research/programs/scientific-feasibility 
Summary:
This project aims to use artificial intelligence to develop a system that evaluates whether a claim is scientifically feasible or not, using a combination of literature search, code-based simulation, and other techniques.

Next-Generation Teams
PI: Adarsh Pyarelal (The University of Arizona)
Co-PIs: Clayton Morrison, Kobus Barnard, Winslow Burleson (The University of Arizona)
Key Personnel: Payal Khosla (The University of Arizona)
Collaborators: Evan Carter (Army Research Laboratory)
Funding: U.S. Army Contracting Command, $882,546
Project Dates: September 1, 2025 – August 31, 2026
Website: wiki.lab.pyarelal.xyz/books/projects/page/next-generation-teams
Summary:
The Next Generation Teams project will conduct experiments to study the structured communication protocols that exist on workplace and other teams that use AI agents, the interventions AI agents use to correct deviations from those protocols, and the effects of AI on team performance, coordination, creativity and plan recognition.

DASS: A Framework for Smart Contract Wills
PI: Clayton Morrison
Funding: National Science Foundation, $748,328
Project Dates: October 2022 – September 2026
Publications:
“A Framework to Retrieve Relevant Laws for Will Execution,” Proceedings of the Natural Legal Language Processing Workshop, 2025
“Classify First, and Then Extract: Prompt Chaining Techniques for Information Extraction,” The 6th Natural Legal Language Processing Workshop, 2024
“Information Extraction from Legal Wills: How Well Does GPT-4 Do?” Findings of EMNLP, 2023
“Validity Assessment of Legal Will Statements as Natural Language Inference,” Findings of the Association for Computational Linguistics, 2022
Website: ml4ai.github.io/nli4wills-corpus 
Summary: Researchers are developing accountable software by combining expertise in the law with techniques from natural language processing and formal methods for verifiable software generation and execution. By accountable, this means that the software will (1) verifiably follow all applicable rules and laws, (2) adapt appropriately to changes in laws, and (3) be explainable, so that non-programmers can understand what the code does and how it relates to what they intend. The project consists of a collaboration between the University of Arizona’s College of Information Science, James E. Rogers College of Law and Department of Computer Science.

Scientific Knowledge Extraction and Model Analysis (SKEMA)
PI: Adarsh Pyarelal
Funding: Lum.ai, Defense Advanced Research Projects Agency, $1,433,646
Project Dates: December 2018 – April 2024
Publications:
“Variable Extraction for Model Recovery in Scientific Literature,” First Workshop on AI and Scientific Discovery: Directions and Opportunities, 2025
“When and Where Did it Happen? An Encoder-Decoder Model to Identify Scenario Context,” Findings of the Association for Computational Linguistics, 2024 
“An Overview and Detail Layout for Visualizing Compound Graphs,” IEEE VIS, 2024 
“Learning Open Domain Multi-hop Search Using Reinforcement Learning,” NAACL Workshop SUKI: Structured and Unstructured Knowledge Integration, 2022
“MathAlign: Linking Formula Identifiers to their Contextual Natural Language Descriptions,” Proceedings of the 12th Edition of the Language Resources and Evaluation Conference, 2020
“AutoMATES: Automated Model Assembly from Text, Equations, and Software,” Modeling the World’s Systems, 2019
Website: www.darpa.mil/research/programs/automating-scientific-knowledge-extraction-modeling
Summary: Under the DARPA Automating Scientific Knowledge Extraction and Modeling program, researchers developed SKEMA, a framework for extracting science models from software, text and equations. Applications include epidemiology models (e.g., COVID-19) and space weather.