aelahi6@uic.edu
Ali Elahi

I am pursuing my Ph.D. at the University of Illinois Chicago under the guidance of Dr. Barbara Di Eugenio and Dr. Michael Curry. My research focuses on Machine Learning, Language Models, and Economics and Computation.

I worked with Dr. Cornelia Caragea on domain adaptation and Transfer Learning during my M.S. at UIC., and I received my bachelor's degrees in Computer Engineering and Mechanical Engineering at the University of Tehran in 2022. I researched recommendation algorithms and their online and offline evaluations during my undergraduate studies. In 2016, I won Iran's National Bronze Medal in Chemistry Olympiad.

Google Scholar, Github

Preprints.

MIRT: Transformers for Truthful Generative Auctions with Whole-feed Permutation Externalities
Meta Collaboration.

Confidence Composition for Multiagent Language Model Systems
By Ali Elahi, Michael J. Curry, Barbara Di Eugenio.

Publications.

Elahi, A., (NeurIPS 2025 GenAI in Finance Workshop). Identifying Financial Risk Information Using RAG with a Contrastive Insight.

09/23/2025 In Press at ACS - ES&T Journal, Paper on Domain Adaptation for Water Quality Prediction.

Elahi, A., Shumway, D., Caragea, C., Caragea D., Dorevitch S., (2024, BigData). Predicting Surface Water Bacteria Levels Using Transfer Learning and Domain Adaptation [Download]

Elahi, A., Taghvaei, F. (2024, BigData). Combining Financial Data and News Articles for Stock Price Movement Prediction by Prompting Large Language Models [Download]

Elahi, A., Zirak, A. (2021, Arxive). A Comparative Study of Recommendation Algorithms: Online and Offline Evaluations on a Large-scale Recommender System [Download]

Presentations & Teaching.

Poster on Confidence for Colaborative Reasoning

Guest Lecture on Social Choice, at Economics and Computation class, April 13, 2026

Teaching Assistant, Economics and Computation, Dr. Michael Curry, Spring 2026

Talk at UIC on Recent Confidence Estimation Methods in LLMs. [Slides]

IEEE BigData Conference: Domain Adaptation in Surface Water Bacteria Level Prediction. [Slides]

CS594: Socially Responsible Language Models; Talk on Bias and Toxicity Mitigation [Slides] and Hallucination Mitigation [slides]