Avatar

Li "Harry" Zhang  张力


About Me

I will be an assistant professor at Drexel University, starting in December 2024. I am looking for 1 to 2 PhD students to start in Spring or Fall 2025. Prospective students have an opportunity for immediate collaboration and should email me to demonstrate an interest in my ongoing or related work.

I am a 5th- and final-year PhD student researcher focusing on Natural Language Processing and Artificial Intelligence, having the honor to be mentored by Prof. Chris Callison-Burch at the University of Pennsylvania. My thesis committee includes Prof. Dan Roth, Prof. Rada Mihalcea, Prof. Graham Neubig, Dr. Marianna Apidianaki, and Prof. Mark Yatskar. I got my BS from the University of Michigan in 2018, mentored by Prof. Rada Mihalcea and Prof. Dragomir Radev.
CV

zharry@seas.upenn.edu


Affiliations

Drexel Universitydrexel logo
Assistant Professor;
Dec 2024 to Future

University of Pennsylvaniaupenn logo
Ph.D.; Aug 2019 to Aug 2024

Allen Institute for Artifical IntelligenceAI2
Research Intern;
April 2023 to Dec 2023

IBM ResearchIBM Research
Research Intern; May 2021 to Aug 2021,
April 2019 to June 2019

University of Michiganumich logo
B.S.E.; Aug 2015 to Dec 2018

Goldman SachsGoldman Sachs
Summer Analyst;
May 2017 to Aug 2017

Shenzhen Middle SchoolSMS logo
High School Diploma;
Sept 2012 to Jun 2015

Mentorship and Teaching

Mentored Students
Tianyi Zhang, University of Pennsylvania
Hainiu Xu, King's College London
Zhaoyi Hou, University of Pittsburg
Young-Min Cho, University of Pennsylvania
Manni Arora, Apple

I mentored each for more than 1 year. All graduated with a Master's degree from the University of Pennsylvania.


Teaching AssistantPenn
2020

CIS 530: Computational Linguistics (Winter, Fall 2020)


Teaching AssistantUM-Penn
2016 - 2018

EECS 595: Natural Language Processing (Fall 2018) and EECS 280: Programming and Introductory Data Structures (Winter, Fall 2016)


Service

I have reviewed more than 50 papers of and chaired for many NLP conferences and workshops.

Area Chair of ARR Feb 2024 (ACL 2024)
Reviewer of LREC-COLING 2024
Reviewer of EMNLP 2023
Program Chair of MASC-SLL 2023
Reviewer of ACL 2023
Program Chair of DaSH Workshop @ EMNLP 2022
Reviewer of COLING 2022
Reviewer of ARR Nov 2021, Mar 2022
Reviewer of LREC 2022
Program Chair of MASC-SLL 2021
Session Chair of AACL-IJCNLP 2020
Co-organizer of CLUNCH 2020
Reviewer of COLING 2020
Reviewer of Computer Speech and Language 2018


Research

Primary Work: Structured Reasoning of Events using LLMs

Events and procedures play a major role in human language. Therefore, reasoning about them is crucial for AI and NLP. My work combines data-driven methods like large language models (LLM) and symbolic, structured representations of events to advance state-of-the-art on many downstream tasks, such as question answering, dialog, script generation, classical planning, etc. Roughly, I have looked into three types of methods:


1. (ongoing) Use LLMs to predict a structured, fully symbolic representation of events (e.g., in PDDL or Python), to be executed by symbolic solvers (e.g., planners or interpreters) for a more precise and deterministic reasoning process.

[29] PDDLEGO: Iterative Planning in Textual Environments; Li Zhang, Peter Jansen, Peter Clark, Chris Callison-Burch and Niket Tandon; in *SEM 2024.Paper BibTeX Repo


[28] PROC2PDDL: Open-Domain Planning Representations from Texts; Tianyi Zhang*Equal contribution^Mentored student, Li Zhang*Equal contribution, Zhaoyi Hou^Mentored student, Ziyu Wang^Mentored student, Yuling Gu, Peter Clark, Chris Callison-Burch and Niket Tandon; in ACL 2024 2st Workshop on Natural Language Reasoning and Structured Explanations.Paper BibTeX Repo


2. Use LLMs to predict a structured, semi-symbolic representation of events (specifically, entities), which helps their decision making and reasoning via in-context learning.

[23] OpenPI2.0: An Improved Dataset for Entity Tracking in Texts; Li Zhang, Hainiu Xu^Mentored student, Abhinav Kommula, Chris Callison-Burch and Niket Tandon; in EACL 2024.Paper BibTeX Repo

[19] Causal Reasoning of Entities and Events in Procedural Texts; Li Zhang*Equal contribution, Hainiu Xu*Equal contribution^Mentored student, Yue Yang, Shuyan Zhou, Weiqiu You, Manni Arora and Chris Callison-Burch; in Findings of EACL 2023.Paper BibTeX Repo


3. Finetune LLMs with language-based data (specifically, event relations) to improve performance on various downstream tasks.

[6] Reasoning about Goals, Steps, and Temporal Ordering with WikiHow; Li Zhang*Equal contribution, Qing Lyu*Equal contribution and Chris Callison-Burch; in EMNLP 2020.Paper BibTeX Repo

[15] Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models; ... Li Zhang*Equal contribution, Qing Lyu*Equal contribution and Chris Callison-Burch; in TMLR.Paper

[10] Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data; Shuyan Zhou*Equal contribution, Li Zhang*Equal contribution, Yue Yang, Qing Lyu, Pengcheng Yin, Chris Callison-Burch and Graham Neubig; in ACL 2022.Paper BibTeX Demo Repo

[8] Goal-Oriented Script Construction; Qing Lyu*Equal contribution, Li Zhang*Equal contribution and Chris Callison-Burch; in INLG 2021.Paper BibTeX Repo

[7] Intent Detection with WikiHow; Li Zhang, Qing Lyu, Chris Callison-Burch; in AACL-IJCNLP 2020.Paper BibTeX Repo

[9] Visual Goal-Step Inference using wikiHow; Yue Yang, Artemis Panagopoulou, Qing Lyu, Li Zhang, Mark Yatskar and Chris Callison-Burch; In EMNLP 2021.Paper BibTeX


Activities


Music

I am a drummer, producer and video content creator. I run a video channel with over 50,000 subscribers on Bilibili and YouTube, primarily making cover songs from video game and anime soundtracks, in a variety of styles ranging from metal to jazz. I am proudly sponsored by Vater, Tama, Mackie, Alesis, NUX, Xvive and have collaborated with manufacturers of major video games such as Genshin Impact and Azur Lane. I also engage in research of AI music generation, having published a paper on automatic drum composition in an AAAI 2023 workshop.
bilibili        

[18] Language Models are Drummers: Drum Composition with Natural Language Pre-Training; Li Zhang and Chris Callison-Burch; in AAAI 2023 Workshop on Creative AI Across Modalities.Paper Repo BibTeX


My two albums A Doll's Lament (reimagined NieR soundtracks) and Dazzling Tales (reimagined Genshin Impact soundtracks) are available for listening on all major streaming platforms.

A Doll's Lament   Dazzling Tales