Yating Wu

Yating Wu
Hi, y'all, I'm a Ph.D. candidate from the ECE department at UT Austin, supervised by Prof. Jessy Li and Prof. Alex Dimakis. My research interests focus on natural language processing and computational linguistics. Outside research, I love soccer, table tennis and Japanese. You can find my CV here.
I am on the 2026-2027 academic and industry job markets. Please feel free to reach out by email if there may be a fit.

Research Overview

Research Delta

I want AI systems to retain context, check their reasoning, and recognize what matters. I approach these goals through questions raised by texts and tasks, building on Questions Under Discussion (QUD).

  1. Retaining context. I use QUD to connect passages to preceding context. Agent memory similarly preserves earlier findings with their evidence and reasoning. Building on this work, I am now helping agents learn from experience without repeating earlier runs' work. Selected work: QUD parsing; ContextWeaver; ContextGraph (in progress)
  2. Checking reasoning. I check model interpretations against context, revealing errors common metrics miss. I also measure structural repetition in model outputs. Extending QUDeval, I now examine whether evidence supports AI responses to human feedback and whether agents follow action limits. Selected work: QUDeval; QUDsim
  3. Recognizing what matters. I separate what to explain from how to explain it. I predict important questions, including for scientific figures. I now study how AI chooses observations and revises research plans as evidence arrives, starting in astronomy with CosmicAI. Selected work: QSalience (EMNLP 2024 Outstanding Paper); ElabQUD; Multimodal QUD

Education

Ph.D., (Aug. 2022 - Now) in Computer Engineering
M.S., (Jan. 2020 - Aug. 2022) in Computer Engineering
Department of Electrical and Computer Engineering,
University of Texas at Austin.
Advisors: Prof. Jessy Li, Prof. Alex Dimakis
Group: UT NLP Group, Wireless Networking and Communications Group(WNCG)
B.Eng., (Spt. 2014 - Jul. 2019) in Computer Science and Technology
B.A., (Spt. 2014 - Jul. 2019) in Japanese
Department of Computer Science
Dalian University of Technology.
Undergraduate Exchange Student, (Spt. 2017 - Aug. 2018) in Computer Science
Department of Information & Communication Engineering,
The University of Tokyo.
Advisor: Prof. Toshihiko Yamasaki
Group: Aizawa-Yamasaki Laboratory (now Aizawa-Yamakata-Matsui Laboratory)

Selected Publications

†Indicates equal contribution.

Awards

Experience

Working Experience

Teaching Experience

Services

RESEARCHResearch Delta
Questions under discussion
2023QUD parsingDiscourse structure 2023QUDevalEvaluating the questions 2025QUDsimComparing texts 2023ElabQUDExplaining added details 2024QSalienceWhich questions matter? 2026MQUDQuestions from figures 2024Bilingual disfluenciesPredictability in speech 2026ContextWeaverMemory for agents
Rivers group research themes.Arrows mark connections between papers.

2023 · Findings of ACL

QUD parsing

Project paper

A parser connects each sentence to an earlier sentence through the implicit question it answers.

Connection to QUDeval QUDeval develops a human evaluation protocol for QUD parsing and examines the questions produced by parsing systems. Abstract ↗

Connection to QSalience QUD parsing recovers the questions a text answers. QSalience asks which questions would most help a reader understand that text. Section 2 ↗

Connection to ContextWeaver QUD parsing connects each sentence to an earlier sentence through the implicit question it answers. ContextWeaver links each reasoning step of an agent to the earlier steps it depends on. Section 3 ↗

2023 · EMNLP

QUDeval

Project paper

Four linguistic criteria test whether a generated question fits its anchor, answer, and preceding text.

Connection to QUD dependency parsing QUDeval develops a human evaluation protocol for QUD parsing and examines the questions produced by parsing systems. Abstract ↗

Connection to QUDsim QUDsim cites QUDeval in its question generation procedure, then uses answerability across documents to measure discourse similarity. Section 4 ↗

Connection to QSalience QSalience follows QUDeval’s constraint that a question must be grounded in its anchor sentence when judging question validity. Section 3 ↗

2025 · COLM

QUDsim

Project paper

The questions answered by two documents reveal similarities in how they develop their ideas.

Connection to QUDeval QUDsim cites QUDeval in its question generation procedure, then uses answerability across documents to measure discourse similarity. Section 4 ↗

2023 · EMNLP

ElabQUD

Project paper

Implicit questions describe the explanations editors add when simplifying an article.

Connection to QSalience QSalience cites ElabQUD to motivate choosing which concepts need an explanation, beyond generating possible elaborations. Section 2 ↗

2024 · EMNLP

QSalience

Outstanding Paper Award
Project paper

We predict how much answering a question would help a reader understand the preceding text.

Connection to QUD dependency parsing QUD parsing recovers the questions a text answers. QSalience asks which questions would most help a reader understand that text. Section 2 ↗

Connection to QUDeval QSalience follows QUDeval’s constraint that a question must be grounded in its anchor sentence when judging question validity. Section 3 ↗

Connection to ElabQUD QSalience cites ElabQUD to motivate choosing which concepts need an explanation, beyond generating possible elaborations. Section 2 ↗

Connection to MQUD MQUD draws on QSalience when extending question salience from news text to scientific figures and a paper’s research goals. Section 2 ↗

2026 · Under submission

MQUD

Project paper

Scientific figures raise questions about a paper’s argument. MQUD studies those questions with annotations from the papers’ authors.

Connection to QSalience MQUD draws on QSalience when extending question salience from news text to scientific figures and a paper’s research goals. Section 2 ↗

2024 · ICML · LLMs and Cognition Workshop

Bilingual disfluencies

Project paper

Language model surprisal and linguistic features help us study disfluencies in monolingual and bilingual speech.

2026 · Under submission

ContextWeaver

Project paper

Dependencies between an agent’s reasoning steps guide which observations and decisions to retain in context.

Connection to QUD dependency parsing QUD parsing connects each sentence to an earlier sentence through the implicit question it answers. ContextWeaver links each reasoning step of an agent to the earlier steps it depends on. Section 3 ↗

Department of Electrical and Computer Engineering
The University of Texas at Austin
The University of Tokyo