Shane Storks profile image

Shane Storks, PhD (he/him)

I’m a postdoctoral research fellow at the University of Michigan Weinberg Institute for Cognitive Science working at the intersection of natural language processing (NLP) and cognitive science. My research leverages insights from how humans learn and reason with language to better understand the capabilities of AI language models and improve their effectiveness. I also appraise the broader impacts of these models and other research trends to inform NLP practice and policy. I strive to promote diversity and opportunity in STEM by volunteering with Queer in AI and Macomb Science Olympiad, and I recently served as a D&I Chair at ACL 2025.

Education
  • University seal.
    Doctor of Philosophy in Computer Science and Engineering

    2024, University of Michigan
    Dissertation: Coherent Physical Commonsense Reasoning in Foundational Language Models
    Advisor: Dr. Joyce Chai

  • University seal.
    Master of Science in Computer Science and Engineering

    2021, University of Michigan

  • University seal.
    Bachelor of Science in Mathematics and Computer Science

    2018, Lawrence Technological University

Research publications, preprints, and presentation materials. * indicates equal contribution.

2025

    Publication preview image. Open preprint or publication for readable version.
    Transparent and Coherent Procedural Mistake Detection
    Shane Storks, Itamar Bar-Yossef, Yayuan Li, Zheyuan Zhang, Jason J. Corso, and Joyce Chai
    Proceedings of EMNLP 2025 -- Suzhou, China

    Publication preview image. Open preprint or publication for readable version.
    Mind the Gap: How BabyLMs Learn Filler-Gap Dependencies
    Chi-Yun Chang, Xueyang Huang, Humaira Nasir, Shane Storks, Olawale Akingbade, and Huteng Dai
    Proceedings of EMNLP 2025 -- Suzhou, China

    Publication preview image. Open preprint or publication for readable version.
    Sparse Feature Coactivation Reveals Composable Semantic Modules in Large Language Models
    Ruixuan Deng*, Xiaoyang Hu*, Miles Gilberti*, Shane Storks*, Aman Taxali, Mike Angstadt, Chandra Sripada, and Joyce Chai
    NeurIPS 2025 Workshop on CogInterp: Interpreting Cognition in Deep Learning Models -- San Diego, CA, USA

    Publication preview image. Open preprint or publication for readable version.
    Discovering Properties of Inflectional Morphology in Neural Emergent Communication
    Miles Gilberti, Shane Storks, and Huteng Dai
    arXiv:2508.05843 [cs.CL]

2024

    Publication preview image. Open preprint or publication for readable version.
    Eliciting In-Context Learning in Vision-Language Models for Videos Through Curated Data Distributional Properties
    Keunwoo Peter Yu, Zheyuan Zhang, Fengyuan Hu, Shane Storks, and Joyce Chai
    Proceedings of EMNLP 2024 -- Miami, FL, USA

2023

    Publication preview image. Open preprint or publication for readable version.
    From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning
    Zheyuan Zhang*, Shane Storks*, Fengyuan Hu, Sungryull Sohn, Moontae Lee, Honglak Lee, and Joyce Chai
    Proceedings of EMNLP 2023 -- Singapore

    Publication preview image. Open preprint or publication for readable version.
    Can Foundation Models Watch, Talk, and Guide You Step By Step to Make a Cake?
    Yuwei Bao, Keunwoo Peter Yu, Yichi Zhang, Shane Storks, Itamar Bar-Yossef, Alex de la Iglesia, Megan Su, Xiao Lin Zheng, and Joyce Chai
    Findings of EMNLP 2023 -- Singapore

    Publication preview image. Open preprint or publication for readable version.
    NLP Reproducibility For All: Understanding Experiences of Beginners
    Shane Storks, Keunwoo Yu, Ziqiao Ma, and Joyce Chai
    Proceedings of ACL 2023 -- Toronto, ON, Canada

    Publication preview image. Open preprint or publication for readable version.
    In-Context Analogical Reasoning with Pre-Trained Language Models
    Xiaoyang Hu*, Shane Storks*, Richard L. Lewis, and Joyce Chai
    Proceedings of ACL 2023 -- Toronto, ON, Canada

    Publication preview image. Open preprint or publication for readable version.
    SEAGULL: An Embodied Agent for Instruction Following Through Situated Dialog
    Yichi Zhang, Jianing Yang, Keunwoo Yu, Yinpei Dai, Shane Storks, Yuwei Bao, Jiayi Pan, Nikhil Devraj, Ziqiao Ma, and Joyce Chai
    Alexa Prize SimBot Challenge Proceedings

2022

    Publication preview image. Open preprint or publication for readable version.
    DANLI: Deliberative Agent for Following Natural Language Instructions
    Yichi Zhang, Jianing Yang, Jiayi Pan, Shane Storks, Nikhil Devraj, Ziqiao Ma, Keunwoo Peter Yu, Yuwei Bao, and Joyce Chai
    Proceedings of EMNLP 2022 -- Abu Dhabi, United Arab Emirates

    Publication preview image. Open preprint or publication for readable version.
    Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative Facts
    Shane Storks, Qiaozi Gao, Aishwarya Reganti, and Govind Thattai
    AAAI-22 Workshop on Combining Learning and Reasoning: Programming Languages, Formalisms, and Representations -- Vancouver, BC, Canada

2021

    Publication preview image. Open preprint or publication for readable version.
    Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding
    Shane Storks, Qiaozi Gao, Yichi Zhang, and Joyce Chai
    Findings of EMNLP 2021 -- Punta Cana, Dominican Republic

    Publication preview image. Open preprint or publication for readable version.
    Beyond the Tip of the Iceberg: Assessing Coherence of Text Classifiers
    Shane Storks and Joyce Chai
    Findings of EMNLP 2021 -- Punta Cana, Dominican Republic

    Publication preview image. Open preprint or publication for readable version.
    Are We There Yet? Learning to Localize in Embodied Instruction Following
    Shane Storks, Qiaozi Gao, Govind Thattai, and Gokhan Tur
    AAAI-21 Workshop on Hybrid Artificial Intelligence -- Online

2020

    Publication preview image. Open preprint or publication for readable version.
    Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches
    Shane Storks, Qiaozi Gao, and Joyce Y. Chai
    arXiv:1904.01172 [cs.CL]

Other talks and guest lectures.

2025

    Transparent and Coherent Procedural Mistake Detection
    Poster Session, August 2025
    Towards Knowledge Foundation Models (KnowFM) Workshop at ACL 2025 -- Vienna, Austria

    Evaluating Commonsense Reasoning in Foundational Language Models
    Guest Lecture, April 2025
    LING 702: Language & Information, University of Michigan -- Ann Arbor, MI, USA

    Foundation Models for Adaptable, Explainable, and Coherent Procedural Understanding
    Invited Talk, February 2025
    Computational Communication Analysis (CoCoA) Lab, University of Michigan -- Flint, MI, USA

2024

    Large Vision-Language Models for Task Guidance and Explainable Mistake Detection
    Poster Session, December 2024
    DARPA PTG PI Meeting at University of Central Florida -- Orlando, FL, USA

2023

    Making Generative AI Better for You: Fine-Tuning & Experimentation for Custom Research Solutions
    Tutorial, November 2023
    Michigan Institute for Data Science (MIDAS) Generative AI Tutorial Series -- Ann Arbor, MI, USA

    Commonsense Reasoning in Natural Language Understanding
    Guest Lecture, November 2023
    EECS 595: Natural Language Processing, University of Michigan -- Ann Arbor, MI, USA

    From Heuristic to Analytic: Cognitively Motivated Strategies for Coherent Physical Commonsense Reasoning
    Invited Talk, November 2023
    2023 Office Day at LG AI Research Global AI Center -- Ann Arbor, MI, USA

    Cognitive Motivations in Analogical and Physical Reasoning with Large Language Models
    Invited Talk, October 2023
    Weinberg Institute for Cognitive Science Seminar at University of Michigan -- Ann Arbor, MI, USA

    NLP Reproducibility for All: Understanding Experiences of Beginners
    Poster Session, October 2023
    Michigan AI Symposium -- Ann Arbor, MI, USA

    Prompt Engineering with LLMs: Basics and Research Applications
    Tutorial, July 2023
    Generative AI for Research Faculty Workshop at University of Michigan -- Ann Arbor, MI, USA

    Harnessing Language and Vision Foundation Models for Action-Effect Prediction
    Poster Session, April 2023
    NLP @ Michigan Day -- Ann Arbor, MI, USA

2022

    Language Model Prompting
    Guest Lecture, November 2022
    EECS 595: Natural Language Processing, University of Michigan -- Ann Arbor, MI, USA

    Large Pre-Trained Language Models for Physical Action Understanding and Planning
    Invited Talk, October 2022
    2022 Microsoft Turing Academic Program (MS-TAP) Workshop -- Online

    Learning Physical Action Schemas from Language and Experience
    Poster Session, September 2022
    DARPA PTG Site Visit at University of Michigan -- Ann Arbor, MI, USA

    Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding
    Poster Session, May 2022
    NLP @ Michigan Day (Best Poster) -- Ann Arbor, MI, USA

    Toward Coherent Commonsense Language Understanding in Machines
    Guest Lecture, January 2022
    EECS 692: Advanced Artificial Intelligence, University of Michigan -- Ann Arbor, MI, USA

2021

    Language Model Prompting
    Guest Lecture, December 2021
    EECS 595: Natural Language Processing, University of Michigan -- Ann Arbor, MI, USA

2018

    Simulating Hot Topic Popularity with a Modified SIR Model
    Invited Talk, February 2018
    Lawrence Technological University Campus Open House -- Southfield, MI, USA

2017

    Simulating Hot Topic Popularity with a Modified SIR Model
    Contributed Talk, July 2017
    Mathematical Association of America MathFest -- Chicago, IL, USA

Courses I've instructed. If you want to learn more, feel free to send me an email!

University logo
LING 321/COMPFOR 250: Alien Anatomy: How ChatGPT Works
Fall 2025

Instructor of Record, University of Michigan

Non-computer science major introductory course about generative AI large language models (LLMs) co-led with Andrew McInnerney. Topics included language modeling, basics of machine learning and neural networks, neural language models and transformers, and the applications and impacts of LLMs.

Weinberg Institute for Cognitive Science
University logo
EECS 595/LING 541/SI 561: Natural Language Processing (NLP)
Fall 2022

Graduate Student Instructor, University of Michigan

Electrical Engineering and Computer Science (EECS)
University logo
EECS 595/LING 541/SI 561: Natural Language Processing (NLP)
Fall 2021

Graduate Student Instructor, University of Michigan

Electrical Engineering and Computer Science (EECS)
University logo
EECS 595/LING 541/SI 561: Natural Language Processing (NLP)
Fall 2020

Graduate Student Instructor, University of Michigan

Graduate introductory NLP course led by Joyce Chai. Topics included linguistics and machine learning basics, statistical and neural language models, and their applications in common tasks like information extraction, machine translation, and dialogue systems.

Electrical Engineering and Computer Science (EECS)

History of academic appointments.

Weinberg Institute for Cognitive Science, University of Michigan
October 2024 - Present

Postdoctoral Research Fellow

Postdoctoral research fellowship focused on interdisciplinary research in generative AI and cognitive science.

Ann Arbor, MI, USA
Computer Science & Engineering Division, University of Michigan
August 2019 - September 2024

Graduate Student Research Assistant (GSRA) & Graduate Student Instructor (GSI)

Research and teaching assistantships during PhD; GSI roles were during Fall 2020, 2021, and 2022 semesters.

Ann Arbor, MI, USA
Michigan State University
August 2018 - July 2019

University Fellow

Financial support award during first year of doctoral study (before moving to University of Michigan).

East Lansing, MI, USA

Other appointments I've held in industry.

Amazon Alexa AI
June 2021 - August 2021

Applied Scientist Intern, Natural Understanding/Teachable AI

Completed a research project on multi-hop reasoning advised by mentors Qiaozi Gao and Govind Thattai.

Sunnyvale, CA, USA
Amazon Alexa AI
June 2020 - August 2020

Applied Scientist Intern, Natural Understanding/Teachable AI

Completed a research project on embodied instruction following advised by mentor Qiaozi Gao.

Sunnyvale, CA, USA
Universal Logistics Holdings, Inc.
January 2017 - July 2018

Junior .NET Developer and Data Analyst

Warren, MI, USA
Dominion Technologies Group, Inc.
June 2016 - December 2016

Junior Programmer

Roseville, MI, USA
Dominion Technologies Group, Inc.
September 2015 - June 2016

Technical Assistant

Roseville, MI, USA
Selected awards and other honors I've received.
Students I've collaborated with and advised on research at the University of Michigan. If you're a University of Michigan student interested in my research and would like to work with me, please send me an email.

Unpublished course projects and side projects. Ask me about them if you're interested!

2021

    Publication preview image. Open preprint or publication for readable version.
    Invariant Extended Kalman Filter for Localization in Underwater Caves
    Samuel Ansaldo, AJ Bull, Xinyu Ma, Alyssa Scheske, and Shane Storks
    EECS 568 (Mobile Robotics), University of Michigan

2020

    Publication preview image. Open preprint or publication for readable version.
    Toward More Faithful Vision-and-Language Navigation Agents
    Shane Storks, Tianrong Zhang, and Wenyi Wu
    EECS 598 (Special Topics: Situated Language Processing for Embodied AI), University of Michigan

2019

    Publication preview image. Open preprint or publication for readable version.
    Using Twitter to Rank Musical Artist Popularity
    Shane Storks and Andrew Schmidt
    CSE 881 (Data Mining), Michigan State University