Yulia Tsvetkov
politics
stress test
political communication
survey
information warfare
agenda-setting
summarization
framing
text generation
large language models
bias
llm
social media
language generation
diffusion language models
35
presentations
41
number of views
2
citations
SHORT BIO
I am an assistant professor in the Paul G. Allen School of Computer Science & Engineering, at the University of Washington. I'm also an adjunct professor at the Language Technologies Institute at CMU. I work on Natural Language Processing–a subfield of computer science focusing on computational processing of human languages. I am particularly interested in hybrid solutions at the intersection of machine learning and theoretical or social linguistics, i.e., solutions that combine interesting learning/modeling methods and insights about human languages or about people speaking these languages.
Much of my research group's work focuses on NLP for social good, multilingual NLP, and language generation. This research is motivated by a unified goal: to extend the capabilities of human language technology beyond individual populations and across language boundaries, thereby enabling NLP for diverse and disadvantaged users, the users that need it most.
Previously, I was an assistant professor in the Language Technologies Institute, School of Computer Science at Carnegie Mellon University, and before that a postdoc in the Stanford NLP Group. I got my PhD from CMU.
Presentations
Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration
Shangbin Feng and 5 other authors
Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks
Yichen Wang and 7 other authors
Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models
Wenxuan Ding and 6 other authors
DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection
Herun Wan and 5 other authors
What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection
Shangbin Feng and 5 other authors
Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers
Roy Xie and 3 other authors
SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation
Abe Bohan Hou and 9 other authors
BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer
Akari Asai and 8 other authors
P^3Sum: Preserving Author’s Perspective in News Summarization with Diffusion Language Models
Yuhan Liu and 6 other authors
On the Blind Spots of Model-Based Evaluation Metrics for Text Generation
Tianxing He and 6 other authors
Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker
Melanie Sclar and 5 other authors
KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding
Shangbin Feng and 4 other authors
SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control
Xiaochuang Han and 2 other authors
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models
Shangbin Feng and 3 other authors
Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey
Sachin Kumar and 4 other authors
Unsupervised Keyphrase Extraction via Interpretable Neural Networks
Rishabh Joshi and 5 other authors