Zhu Liu (刘柱)

Student at Tsinghua University

liuzhu22 (at) mails (dot) edu (dot) cn

[CV]

About Me

I am a Ph.D. candidate in the School of Humanities at Tsinghua University. My major is computational linguistics, combining artificial intelligence and natural languages. I am interested in computational lexical semantics (including polysemy, ambiguity and uncertainty) and AI interpretability for LLMs.

News

• [January 2025] I just passed mid-term examination by defensing and submitting a report! Thank you for the comments from three committee members (Prof. Mingming Liu, Prof. Xiaoshi Hu, Prof. Ying Liu)!

• [December 2024] Volunteer applications have been accepted by COLING 2025! See you in Abu Dhabi~

• [December 2024] Two papers to CoMeDi Workshop have been accepted!

• [December 2024] ACL SRW 2025 is recruiting mentors and reviewers. Refer to more info here.

• [December 2024] I got the feedback from ARR meta (a little bit negative though) and committed it to NAACL 2025.

• [December 2024] I submitted a thesis proposal on NAACL SRW 2025. Looking forward to the feedback!

Education

• Tsinghua University (PhD Candidate)

  Sept 2022 - May 2026 (Expected)

  Major Computational Linguistics

  courses: Linguistic typology (by Rui Guo, auditing), Morphology (by XiuFang Dong, auditing), Probability and Random Mathematics (by Jun Ye, auditing), Natural Language Processing (by Yue Zhang, online auditing), Topics in Chinese Morphology and Syntax (by Dun Deng, A), Research on Corpus Linguistics (by Ying Liu, A), Research of Seclected Topics on Chinese Semantics (by Bing Qiu, A, Thesis: An Empirical Study on Semantic Relations within Chinese Compound Words based on Word Embeddings)

  Other interesting courses: Appreciation of Western Opera (by Yi Ding, auditing), History of Western Music (by Xiao Kang, auditing), Appreciation of Peking Opera (by Mengmei Zhou)

  Road to Thesis:

  1. A Survey of Word Sense Disambiguation (Thesis of Comprehensive Examination, A)

  2. Aspect of uncertainty in WSD (Conference paper)

  3. Research proposal for thesis (RP) [May, 2024]

  4. Thesis proposal defense for Final Thesis (Chinese RP, PPT) [July, 2024]

  5. Research proposal v2 for thesis (RP) [December, 2024], which was submitted to NAACL SRW 2025

  6. Mid-term Examination Report for Final Thesis (Mid-term Report, PPT)

• Southern University of Science and Technology (Master)

  Sept 2019 - July 2022

  Major: Computer Science

  courses: Advanced Algorithm (A), Bayesian Data Analysis (A), Machine Learning (A)

  Other interesting courses: Translation and Appreciation of Chinese Classical Poetry （by Mengwen Zhu, A), Classics and the Process of Canonization (by Mengwen Zhu, auditing)

  Thesis: Towards Human-like Diverse Video Captioning Via a Latent Generative Model

• Dalian University of Technology (Undergraduate)

  Sept 2015 - July 2019

  Major: Digital Media Techonology

Academic Experiences

• Research Intern in THUNLP, cosupervised by Maosong Sun. Reasearch focuses on LLM interpretability and semantic representation.

  October 2023 -

• Reviewer of EMNLP 2023

• Reviewer of Rep4NLP in ACL'24

• Poster presenter in ACL'24

• Attendee at CCL'24

• Co-chair of ACL'25 Student Research Workshop

• Reviewer of CoMeDi, a workshop in Coling 2025

• Presenter in Sixth Linguistics and Philology Forum, and got first award.

• Volunteer in Coling 2025

Publications & Projects

→ Full list

• Evaluating Distributed Representations for Multi-Level Lexical Semantics: A Research Proposal

  Arxiv (under review)

  [Paper]

• JuniperLiu at CoMeDi Shared Task: Models as Annotators in Lexical Semantics Disagreements

  CoMeDi workshop in Coling 2025

  [Paper] [CODE]

• A Top-down Graph-based Tool for Modeling Classical Semantic Maps: A Crosslinguistic Case Study of Supplementary Adverbs

  Arxiv (under review)

  [Paper] [CODE]

• Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics

  Findings of ACL 2024; CoMeDi workshop in Coling 2025 (non-achival)

  [Paper][CODE] [Poster] [PPT]

• Ambiguity Meets Uncertainty: Investigating Uncertainty Estimation for Word Sense Disambiguation

  Findings of ACL 2023

  [Paper][CODE] [Poster] [PPT]

• Show, Tell and Rephrase: Diverse Video Captioning via Two-Stage Progressive Training

  TMM 2022

  [Paper] [CODE]

Talks

• To know, or not to know? Language, Uncertainty and Artificial Intelligence

  At Shanxi University of Finance and Economnics, June 12th, [PPT]

  In this talk, I reviewed my recent research from a philosophical perspective of epistemology: What does the model not know? (Known Knowns) What does the model unknow? (Known Unknowns).

• Evaluation agentiveness of Subject-object reversible sentences in LLMs

  At a linguistic seminar, November 26th, [PPT]

  In this talk, I employ difference vetors in LLMs to represent agentiveness of different components (SVO) in a reversible but meaning-preserving sentence pair.

• A Top-down Graph-based Tool for Modeling Classical Semantic Maps: A Crosslinguistic Case Study of Supplementary Adverbs

  At a linguistic seminar, November 30th, 2025. [PPT in Chinese] [Paper] [CODE]

  In this talk, I develop a graph algorithm to construct the semantic map automatically. The tool is available now, and feel free to use it.

Awards and Honors

• First Prize for Outstanding Paper at the 6th Youth Academic Forum on Linguistics and Philology at Tsinghua University (2024)

• First-Class University-Level Comprehensive Scholarship of Tsinghua University for the Year 2023

• Outstanding Creative Paper Award at the 8th Shanghai Library Open Data Competition for the Year 2023

• First Prize for Outstanding Paper at the 5th Youth Academic Forum on Linguistics and Philology at Tsinghua University (2023)

• Third Prize for Outstanding Paper at the 4th Youth Academic Forum on Linguistics and Philology at Tsinghua University (2022)

Other Resources:

• A comprehensive repo about lexical ambiguity: Awesome Word Sense Disambiguation.