Liwei Jiang 🌊 姜力炜 Ph.D. Candidate
Paul G. Allen School of Computer Science & Engineering, University of Washington
Contact: lwjiang@cs.washington.edu |
Google Scholar |
LinkedIn |
GitHub |
X
My Ph.D. defense on Humanistic, Pluralistic, and Coevolutionary AI Safety and Alignment is scheduled for May 8, 11:30 AM–12:30 PM PT!
Welcome to join online via Zoom or in person at UW CSE Allen Center 403. Click here to add the event to your Google calendar.
Welcome to join online via Zoom or in person at UW CSE Allen Center 403. Click here to add the event to your Google calendar.
I will soon receive my Ph.D. from the Paul G. Allen School of Computer Science & Engineering at the University of Washington, advised by Yejin Choi, and hold a Bachelor's degree from Colby College. Previously, I was a student researcher at NVIDIA and Allen Institute for Artificial Intelligence (Ai2).
The North Star of my research is to build AI that genuinely benefits humanity. My deeper calling is to inspire and empower young scholars to pursue that same vision and embark on bold intellectual adventures.
Artificial Intelligence
Machine Learning
Natural Language Processing
AI Safety and Alignment
Human-AI Collaborative Intelligence
News
April 2026: My academic job search material for 2025-2026: Job Talk Slides, CV, Research Statement, Teaching Statement, and Service Statement.
Jan 2026: Honored to receive the AI2050 Compute Grant from Schmidt Sciences with 100K hours of NVIDIA H100 compute to advance our research on Pluralistic Alignment.
Dec 2025: Our paper Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond) received the 🏆 Best Paper Award at NeurIPS 2025!
Dec 2025: I'll be traveling to San Diego for NeurIPS 2025 for presenting two
accepted papers: Oral for Artificial Hivemind and poster for AI debates for
controversial claims. I'll
also be attending the Alignment Workshop!
Please feel free to reach out if you'd like to chat!
Nov 2025: Give a guest lectures on In-Context Learning, Prompting, and Basics of Reasoning at CSE 447 (Undergrad NLP) at UW.
Oct 2025: Our paper Chasing Moving
Targets with Online Self-Play Reinforcement
Learning
for Safer Language Models won the 🏆 Outstanding Paper Award at the AIA workshop @ COLM
2025!
Oct 2025: Co-organize the 3rd edition of the Socially Responsible Language Modelling Research (SoLaR)
Workshop at COLM
2025.
July 2025: Co-present our tutorial on Guardrails and Security for LLMs: Safe, Secure, and
Controllable Steering of LLM Applications at ACL 2025! Check out the slides at the tutorial
website!
March/May 2025: Give two guest lectures on Red-Teaming and Safeguarding Language Models: Current
Practices, Challenges, and Future Directions at CMU and UCLA.
March 2025: Started my internship with NVIDIA NeMo Guardrails team and began my visit at Stanford!
January 2025: Our paper Investigating Machine Moral Judgment through the Delphi Experiment is published in Nature Machine Intelligence!
Dec 2024: Co-organize the 2nd edition the Socially Responsible Language Modelling Research (SoLaR)
Workshop at NeurIPS
2024.
Oct/Nov 2024: Give two guest lectures on How to Build AI with Deep Concerns for Human Traits,
Values, and Needs? at UIUC and University of Pittsburgh.
Oct/Nov 2024: Give two guest lectures on LLM Reasoning (In-Context Learning, Prompting, and
Reasoning) at KAIST and UW.
May 2024: Our paper MigraineTracker: Examining Patient
Experiences with Goal-Directed Self-Tracking for a Chronic Health Condition recieved the 🏆
Best Paper Award at CHI 2024!
Jan 2024: Lead of TA effort and co-design (a LLM version!) for the
class
module of CSE 447/517, the undergrad and grad NLP class at UW
CSE.
Dec 2023: Co-organize the AI Meets
Moral Philosophy and Moral Psychology: An Interdisciplinary Dialogue about Computational Ethics (MP2)
Workshop at NeurIPS 2023.
Dec 2023: Our paper SODA:
Million-Scale Dialogue Distillation with Social Commonsense Contextualization recieved the 🏆
Outstanding Paper Award at EMNLP 2023!
July 2022: Our paper NeuroLogic
A*esque Decoding: Constrained Text Generation with Lookahead Heuristics recieved the 🏆
Best Paper Award at NAACL 2022!
June 2020: Started my internship at Ai2!
Publications (*, + indicate equal contribution) Google Scholar
Preprints
Chasing Moving Targets with Online Self-Play Reinforcement Learning
for Safer Language Models
🏆 Outstanding Paper Award (Oral)
AI Agents: Capabilities and Safety (AIA) Workshop @ COLM 2025
HieraSuite: A Holistic Toolkit for Building Versatile System-User Instruction Hierarchy
PluralisticBehaviorSuite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies
PDF
Multi-Turn Interactions in Large Language Models (MTI-LLM) Workshop
@ NeurIPS 2025
WildHallucination: Evaluating Long-Form Factuality in LLMs with Real-World Entity Queries
2026
Spectrum Tuning: Post-Training for Distributional Coverage and In-Context Steerability
ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
2025
Investigating Machine Moral Judgment through the Delphi Experiment
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
Can Language Models Reason about Individualistic Human Values and
Preferences?
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive
Multi-Agents
CulturalBench: Building a Robust, Diverse, and Challenging Cultural
Benchmark by Human-AI CulturalTeaming
AI Debate Aids Assessment of Controversial Claims
PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages
HAICosystem: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions
Position Paper: Political Neutrality in AI is Impossible—But Here is How to Approximate it
SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic
Attribution of Machine Text against Web Text
To Err is AI: A Case Study Informing LLM Flaw Reporting Practices
2024
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially)
Safer Language Models
WildGuard: Open One-Stop Moderation Tools for Safety Risks,
Jailbreaks, and Refusals of LLMs
Culture-Gen: Revealing Global Cultural Perception in Language Models through Natural Language
Prompting
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with
Hypothesis Refinement
Particip-AI: A Democratic Surveying Framework for Anticipating Future AI Use Cases, Harms and
Benefits
Information-Theoretic Distillation for Reference-less Summarization
Position Paper: A Roadmap to Pluralistic Alignment
Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for
Summarization and Paraphrasing
JAMDEC: Unsupervised Authorship Obfuscation Using Constrained Decoding Over Small Language
Models
MigraineTracker: Examining Patient Experiences with Goal-Directed Self-Tracking for a Chronic
Health Condition
The Generative AI Paradox: "What It Can Create, It May Not Understand"
2023
What Makes it Ok to Set a Fire? Iterative Self-distillation of
Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations
NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation
SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization
Reading Books is Great, But Not if You Are Driving! Visually Grounded Reasoning about Defeasible
Commonsense Norms
BiasX: "Thinking Slow" in Toxic Content Moderation with Explanations
of Implied Social Biases
Faith and Fate: Limits of Transformers on Compositionality
2022
Aligning to Social Norms and Values in Interactive Narratives
NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics
ProsocialDialog: A Prosocial Backbone for Conversational Agents
2021
EnglishBot: An AI-Powered Conversational System for Second Language
Learning
2019
QuizBot: A Dialogue-Based Adaptive Learning System for Factual
Knowledge
Awards
🏆 Best Paper Award
NeurIPS 2025 (Dec 2025)
🏆 Outstanding Paper Award
AI Agents: Capabilities and Safety (AIA) Workshop @ COLM 2025 (Oct 2025)
🏆 Best Paper Award
CHI 2024 (May 2024)
🏆 Outstanding Paper Award
EMNLP 2023 (Dec 2023)
🏆 Best Paper Award
NAACL 2022 (Jul 2022)
Anne Dinning - Michael Wolf Endowed Regental Fellowship
University of Washington (2019)
Paul G. Allen School First-Year Ph.D. Fellowship
Member of the Phi Beta Kappa Society
Colby College (2018)
Elected as a member of Phi Beta Kappa with junior standing
Honorable Mention of Interdisciplinary Contest in Modeling (ICM)
COMAP (2018)
20th annual Interdisciplinary Contest in Modeling (ICM)
Phi Beta Kappa Undergraduate Scholastic Achievement Award
Colby College (2017)
Top two students in the sophomore and junior classes
Julius Seelye Bixler Scholar
Colby College (2016, 2017, 2018)
Top-ranking students as determined by the cumulative academic record, three-time
recipient
Phi Beta Kappa Summer Research Scholar
Colby College (2016)
Summer research stipend
Grants
AI2050 Compute Grant (100K hours of NVIDIA H100 compute)
Schmidt Sciences (Jan 2026)
Education & Experience
Education
University of Washington
Ph.D. in Computer Science and Engineering
Sept 2019 - March 2026 (expected), Seattle, Washington
Colby College
B.A. in Computer Science and Mathematics (Summa Cum Laude, Top 0.5%)
Sept 2015 - Jan 2019, Waterville, Maine
Professional Experience
NVIDIA
Research Scientist
April 2026 - Present, Santa Clara, California
Graduate Student Researcher at Nemo-Guardrail Team
March 2025 - March 2026, Santa Clara, California
Allen Institute for Artificial Intelligence (Ai2)
Graduate Student Researcher at Mosaic and AllenNLP Teams
June 2020 - December 2024, Seattle, Washington
Stanford University
Undergraduate Research Intern at the Computer Science Department
June 2017 - September 2019, Stanford, California
The Future Laboratory, Tsinghua University
Visiting Student Researcher
July 2019 - September 2019, Beijing, China
Teaching & Services
Courses
CSE447/517 Natural Language Processing—An LLM Version (Spring 2024, Grad + Undergrad. Instructed by Prof. Yejin Choi)
Head TA for the NLP class with 230+ undergraduate and graduate students
Co-design the class module, including teaching materials and assignments
CSE 599 D1 Exploration on Language, Knowledge, and Reasoning (Winter 2023, Grad, Instructed by Prof. Yejin Choi)
Lead TA for a graduate-level seminar with over 30 students
Conference Tutorials
Guardrails and Security for LLMs: Safe, Secure, and Controllable Steering of LLM Applications
July 2025, Co-Instructor, ACL 2025
Guest Lectures
CSE 447: Natural Language Processing, University of Washington
In-Context Learning, Prompting, and Basics of Reasoning
Slides
Nov 2025 (Instructor: Yulia Tsvetkov)
COM SCI 162: Natural Language Processing, UCLA
Red-Teaming and Safeguarding Language Models: Current Practices, Challenges, and Future Directions
Slides
May 2025 (Instructor: Saadia Gabriel)
11-830: Ethics, Social Biases, and Positive Impact in Language Technologies, CMU
Red-Teaming and Safeguarding Language Models: Current Practices, Challenges, and Future Directions
Slides
Feb 2025 (Instructor: Maarten Sap)
IS504: Sociotechnical Information Systems, UIUC
How to Build AI with Deep Concerns for Human Traits, Values, and Needs?
Slides
Nov 2024 (Instructor: Yue Guo)
CS475: ML for NLP, KAIST, South Korea
LLM Reasoning (In-Context Learning, Prompting, and Reasoning)
Slides
Nov 2024 (Instructor: Alice Oh)
CSE 447: Natural Language Processing, University of Washington
In-Context Learning, Prompting, and Basics of Reasoning
Slides
Nov 2024 (Instructor: Yulia Tsvetkov)
CS1684/2084: Bias and Ethical Implications in Artificial Intelligence, University of Pittsburgh
How to Build AI with Deep Concerns for Human Traits, Values, and Needs?
Slides
Oct 2024 (Instructor: Xiang Lorraine Li)
CSE 163: Intermediate Data Programming, University of Washington
How to Build AI with Deep Concerns for Human Traits, Values, and Needs?
Aug 2024 (Instructor: Yuxuan Mei)
Ethics and Citizenship, The Downtown School, Seattle
Can We Teach Machines Human Ethics and Values?
Sept 2023, w/ Valentina Pyatkin and Taylor Sorensen
CS496: AI Perspectives: Symbolic Reasoning to Deep Learning, Northwestern University
Toward Interpretable and Interactive Socially & Ethically Informed AI
March 2023 (Instructor: Mohammed Anwarul Alam)
LAW E 553: Technology Law And Public Policy Seminar, University of Washington
Toward Interpretable and Interactive Socially & Ethically Informed AI
March 2023 (Instructor: Inyoung Cheong)
Ethics and Citizenship, The Downtown School, Seattle
Toward Socially Aware & Ethically Informed AI
Slides
Sept 2022, w/ Saadia Gabriel
HONORS 222 B: Artificial Intelligence Meets Society, University of Washington
Toward Ethically Informed & Socially Aware AI
May 2022 (Instructor: Richard Freeman)
Workshop Organizations
2nd Edition of Pluralistic Alignment Workshop
July 2026, Co-Organizer, ICML 2026
Human-AI Co-Creativity Workshop
July 2026, Co-Organizer, ICML 2026
3rd Edition of Socially Responsible Language Modelling Research (SoLaR)
Oct 2025, Co-Organizer, COLM 2025
2nd Edition of Socially Responsible Language Modelling Research (SoLaR)
Dec 2024, Co-Organizer, NeurIPS 2024
AI Meets Moral Philosophy and Moral Psychology: An Interdisciplinary Dialogue about Computational Ethics (MP2)
Dec 2023, Co-Organizer, NeurIPS 2023
Talks
UCLA NLP Seminar | UIUC NLP Seminar | UIUC ECE (Hosted by Prof. Huan Zhang)
Humanistic, Pluralistic, and Coevolutionary AI Safety and Alignment
Jan 2026, Speaker
NeurIPS 2025 | NVIDIA | Ploutos | University of Toronto (Hosted by Prof. Ebrahim Bagheri) | Zhiyuan Talk | AI TIME
Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
Slides
Dec 2025, Speaker
Netskope
WildTeaming and WildGuard: Building Robust Model-Level and System-Level Safeguards of Language Models
May 2025, Speaker
Darpa ITM PI Meeting
Can Language Models Reason about Individualistic Human Values and Preferences?
March 2025, Speaker
University of Washington, Foster School of Business, Computational Minds and Machines lab
How to Build Machines with Deep Concerns of Human Traits, Values, and Needs?—Towards Humanistic AI Alignment
Feb 2025, Speaker (Hosted by Prof. Max Kleiman-Weiner)
Annual Research Showcase and Open House Event, UW CSE
AI Safety Panel
Oct 2024, Panelist
All-Ai2 Meeting, Allen Institute for Artificial Intelligence (Ai2)
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer LMs
July 2024, Speaker
The Big Picture Workshop, EMNLP, Singapore
On the Outcomes of Scientific Disagreements on Machine Morality
Dec 2023, Speaker
Darpa ITM Kickoff PI Meeting
Toward Interpretable and Interactive Socially & Ethically Informed AI
May 2023, Speaker
Mosaic Morality & AI Series, Allen Institute for Artificial Intelligence (Ai2)
Toward Interpretable, Interactive, Informative Machine Moral Reasoning
Feb 2023, Discussant
UW NLP Retreat
Toward Socially Aware & Ethically Informed AI
Sept 2022, Speaker
All-Ai2 Meeting, Allen Institute for Artificial Intelligence (Ai2)
Delphi: Toward Machine Ethics and Norms
Oct 2021, Speaker
Bio
Liwei Jiang is a final-year Ph.D. candidate in the Paul G. Allen School of Computer Science & Engineering at the University of Washington, advised by Prof. Yejin Choi. She was previously a graduate student researcher at NVIDIA and the Allen Institute for Artificial Intelligence (Ai2). Her research focuses on humanistic, pluralistic, and coevolutionary AI safety and alignment, where she spearheads research on moral and pluralistic value reasoning in language models and develops data-, algorithm-, and system-level solutions to socio-technical challenges in AI safety, security, and large language model alignment. Her work has received Best Paper Awards at NeurIPS 2025, NAACL 2022, and CHI 2024, as well as Outstanding Paper Awards at EMNLP 2023 and the AIA Workshop at COLM 2025, and has been featured in The New York Times, Nature Outlook, IEEE Spectrum, Wired, and other major media. She co-organizes workshops including MP2 (NeurIPS 2023) and SoLaR (NeurIPS 2024; COLM 2025), and co-leads the Guardrails and Security for LLMs tutorial at ACL 2025.
Personal
One of my biggest life goals is to inspire and support young people from underprivileged backgrounds, especially the next generation of women scientists, so they can pursue ambitious dreams while staying true to themselves.
I firmly believe that everyone has the potential to achieve anything they set their mind to. Keep going and try again.
Your path is uniquely yours. Follow what ignites you. Every twist, every turn, every unexpected direction is exactly where you need to be.
Two cats, an orange tabby named Loopy and an orange british shorthair named Loafy, adopted me as their owner.
My role model: RBG (Ruth Bader Ginsburg).