Welcome to my personal site! I am a postdoctoral researcher at the Allen Institute for AI (Ai2). I am also a member of H2Lab at the University of Washington. I am advised by Ashish Sabharwal and Hannaneh Hajishirzi. I received my PhD from Georgia Tech in 2022, advised by Prof. Mark Riedl. During my PhD I spent time interning at Google, Sutter Health, and Ai2 (2x), and won the Ai2 Outstanding Intern award.
In August, I will be starting as an assistant professor in the CS department at the University of Maryland. If you are a current CS graduate student interested in my research, I’d love to hear from you. I will also be offering a graduate seminar (CMSC848R) on LM interpretability in the fall.
I work on the interpretability and transparency of language models (LMs) and other neural networks, with the goal of increasing their reliability, safety, and performance. I also focus on providing natural language explanations for users of LMs.
Short Bio for Talks
Updates
- Fall 2025: Starting as an assistant professor in the CS department at the University of Maryland. Go terps!
- Summer 2025: Congrats to my undergraduate student Alec Bunn on having a paper accepted to the ACL 2025 GEM workshop.
- Summer 2025: Our Mechanistic Interpretability Benchmark (MIB) was accepted to ICML 2025. Check out the website for all the benchmark resources. I am also organizing the Actionable Interpretability Workshop at ICML. See you in Vancouver!
- Spring 2025: Two papers accepted to ICLR 2025, the former as a spotlight.
- Winter 2024: Selected as a Rising Star in Machine Learning.
- Winter 2024: Recognized as an outstanding area chair at EMNLP 2024.
- Winter 2024: Paper proposing a taxonomy for model noncompliance accepted at NeurIPS 2024 Datasets and Benchmarks.
- Winter 2024: Attending EMNLP in Miami. Checkout our 2 Findings papers and our position paper on mechanistic interpretability at the BlackBoxNLP workshop. Slides from my talk at BlackBoxNLP: here.
- Fall 2024: Attending COLM in Philly.
- Fall 2024: Selected as a Rising Star in Generative AI.
- Summer 2024: Check out our NAACL 2024 tutorial on Explanation in the Era of Large Language Models. See you in Mexico City!
- Spring 2024: Our paper led by my intern Peter Hase, The Unreasonable Effectiveness of Easy Training Data for Hard Tasks, will appear at ACL 2024.
- Spring 2024: Gave a guest lecture in the graduate-level LLMs course at Washington University in St. Louis.
- Winter 2023: Recording of Sarthak Jain and I’s keynote (“Is Attention = Explanation? Past, Present, and Future”) at the Big Picture workshop is available here (from 1:57).
- Winter 2023: Gave a talk to the Washington State Senate’s Environment, Energy, and Technology Committee on “What is AI?”.
- Winter 2023: Recognized as a top reviewer at NeurIPS 2023.
- Winter 2023: Two papers at EMNLP 2023, and giving a keynote at the Big Picture workshop with Sarthak Jain. See you in Singapore!
- Winter 2023: Selected as a Rising Star in EECS.
- Winter 2023: Self-Refine published at NeurIPS.
- Fall 2023: Talks at UC Irvine, UCSD, and USC.
- Summer 2023: Slides and recording (from 7:45) of my keynote at the ACL Natural Language Reasoning and Structured Explanations workshop are available.
- Summer 2023: Awarded an Outstanding Area Chair award (top 1.5% of reviewers and chairs) at ACL 2023.
- Spring 2023: Quoted in this article about language model interpretability.
- Fall 2022: Talks at various NLP groups at the University of Washington (Tsvetshop, H2Lab, and Treehouse).
- Fall 2022: Two Findings papers at EMNLP 2022.
- Fall 2022: Co-organizing the BlackBoxNLP workshop at EMNLP 2022. See you in Abu Dhabi!
- Fall 2022: I am an area chair for EMNLP 2022.
- Fall 2022: Started postdoc at AI2.
- Summer 2022: Paper on generating few-shot free-text explanations at NAACL 2022.
- Summer 2022: I defended my PhD dissertation!
Contact me
Email: wiegreffesarah[at]gmail[dot]com
How to pronounce my last name (click on German left-side audio)
Older Updates
- Spring 2022: Giving a talk at the Oxford NLP reading group.
- Fall 2021: I passed my PhD dissertation proposal!
- Fall 2021: Paper and companion website– a survey on explainable NLP datasets– accepted to NeurIPS 2021 Datasets & Benchmarks.
- Fall 2021: Paper accepted to EMNLP 2021.
- Fall 2021: I am a TA for CS 7650 Natural Language Processing.
- Summer 2021: I am returning to AI2 to intern on the Mosaic team, working with Swabha Swayamdipta, Jack Hessel, and Yejin Choi.
- Summer 2021: Paper at NAACL 2021 Narrative Understanding workshop.
- Spring-Summer 2021: Publicity Co-Chair for NAACL 2021. Checkout our social initiative People of Natural Language Processing; follow us on Twitter (@NAACLHLT) and Weibo (@国际计算语言学年会ACL2021).
- Spring 2021: I gave a (recorded) talk at NLP with Friends.
- Spring 2021: I am a TA for CS 7643 Deep Learning.
- Summer and Fall 2020: I was a research intern at the Allen Institute for AI, working with Noah Smith and Ana Marasović. Awarded the AI2 Outstanding Intern award!
- Summer 2020: Paper at ACL 2020 with collaborators at Northeastern University.
- Spring 2020: Gave a (recorded) talk at the USC/ISI NLP Seminar: “BlackBox NLP: What are we looking for, and where do we stand?”.
- Fall 2019: Presented a poster at WiML 2019.
- Fall 2019: Paper accepted to EMNLP 2019: Attention is not not Explanation. Recorded talk here.
- Fall 2019: I am a TA for CS 7643 Deep Learning taught by Dhruv Batra. Slides from my guest lecture are here.
- Summer 2019: I am a research intern at Google Medical Brain, working with Dr. Edward Choi and Gerardo Flores.
- Summer 2019: Paper accepted at the ACL BioNLP 2019 workshop: Clinical Concept Extraction for Document-Level Coding
- Spring 2019: I passed my qualifying exam! (in intelligent systems: machine learning and NLP subareas)
- Spring 2019: I am a TA for CS 4641 Machine Learning.
- Spring 2019: Attended ACM FAT* 2019 as a student volunteer.
- Summer 2018: I was an intern at Sutter Health working with the Research, Development and Dissemination Team on deep learning models for outcome prediction using text.
- Summer 2018: Attended NAACL in New Orleans as a student volunteer.
- Spring 2018: Paper accepted to NAACL 2018 (Explainable Prediction of Medical Codes from Clinical Text)
- Spring 2018: Attended the CRA-W Graduate Cohort Workshop in San Francisco, CA.