Liangming Pan

Postdoctoral Scholar

University of California, Santa Barbara (UCSB)

Biography

Liangming Pan (潘亮铭) is a Postdoctoral Scholar at the Natural Language Processing Group, University of California, Santa Barbara (UCSB), working with Prof. William Yang Wang. He obtained his Ph.D. from the National University of Singapore in Jan 2022, jointly advised by Prof. Min-Yen Kan and Prof. Tat-Seng Chua. Before joining NUS, he received Master’s degree from the School of Computer Science at Tsinghua University in June 2017, working with Prof. Juanzi Li and Prof. Jie Tang. He obtained his Bachelor’s degree from Beihang University (2010 - 2014). He was a visiting Ph.D. student from 2020 to 2021, supervised by Prof. William Yang Wang.

His broad research interests include knowledge bases, natural language processing, and data mining. To be specific, his research topics include Question Answering, Question Generation, and Automated Fact Checking.

Interests

Question Answering
Question Generation
Fact Checking
Knowledge Graph

Education

PhD in Computer Science, 2018 — 2022

National University of Singapore
MEng in Computer Science, 2014 — 2017

Tsinghua University
BSc in Software Engineering, 2010 — 2014

Beihang University

News

Announcement: I am on the academic job market for 2024 Fall, with a research focus on factuality, reasoning, and safety of large language models. Open to opportunities worldwide. Feel free to send me an email at liangmingpan@ucsb.edu if your department has open positions. Thanks!

Nov 2023	Our paper Attacking Open-domain Question Answering by Injecting Misinformation received the Area Chair Award (Question Answering) at IJCNLP-AACL 2023.
Oct 2023	I have 8 papers accepted by EMNLP 2023 (4 Main Conference, 3 Findings, 1 Demo). Topics involves logical reasoning, safety, and evaluation of LLMs.
Aug 2023	New Survey Paper! Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies. We also create a paper list.
May 2023	New Preprint! Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning.
May 2023	Our paper Fact-Checking Complex Claims with Program-Guided Reasoning was accepted by the main conference of ACL 2023.
Feb 2023	Our paper Hashtag-Guided Low-Resource Tweet Classification was accepted by WWW 2023.
Feb 2023	Invited Talk "Building Data-efficient and Explainable Fact-Checking Models" at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI).
Dec 2022	I will serve as an Area Chair for the Question Answering track of ACL 2023.
Dec 2022	Starting from Dec 2022, I am thrilled to join the UC Santa Barbara Natural Language Processing Group as a Postdoctoral Scholar, working with Prof. William Yang Wang.
Sep 2022	From September to December, I joined Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) as a short-term Research Fellow, working with Prof. Preslav Nakov.
Aug 2022	Two papers accepted by COLING 2022: CoHS-CQG: Context and History Selection for Conversational Question Generation, and KHANQ: A Dataset for Generating Deep Questions in Education.
Jun 2022	I am thrilled to announce that I have received my Ph.D. degree!
May 2022	One paper accepted by BEA Workshop @ NAACL 2022: Automatic True/False Question Generation for Educational Purpose.
Apr 2022	Talk "Towards generating deep questions from text" at Singapore Management University (SMU).
Apr 2022	One paper accepted by ICMR 2022: Ingredient-enriched Recipe Generation from Cooking Videos.
Mar 2022	Invited talk "Applications of Question Generation in NLP" for Pie & AI: Singapore, organized by deeplearning.ai. [Slides]
Mar 2022	Two papers accepted by ACL 2022 + Findings: KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base (main conference), and Interpreting the Robustness of Neural NLP Models to Textual Perturbations (findings).
Jan 2022	Submitted my Ph.D. thesis "Towards generating deep questions from text"
Aug 2021	Invited talk "Towards generating human-like deep questions" for Monthly NLP Talks at NTU-NLP. [Slides] [Video]
May 2021	One paper accepted by ACL-IJCNLP 2021: Zero-shot Fact Verification by Claim Generation (short paper). [Codes]
Mar 2021	One paper accepted by NAACL 2021: Unsupervised Multi-hop Question Answering by Question Generation (long paper). [Codes]
Feb 2021	An invited talk "Towards generating human-like deep questions" at School of Computing, National University of Singapore.
Jan 2021	I received the Dean's Graduate Research Excellence Award of 2019/2020 Semester 2 from the School of Computing, National University of Singapore.
Nov 2020	I will serve as a Senior Program Committee (SPC) Member for IJCAI 2021
Oct 2020	One paper accepted by COLING 2020: Exploring Question-Specific Rewards for Generating Deep Questions (long paper, acceptance rate: 32.9%). [Codes]
Sep 2020	One paper accepted by EMNLP 2020: Exploring and Evaluating Attributes, Values, and Structure for Entity Alignment (long paper, acceptance rate: 22.4%).
Sep 2020	I received the Research Achievement Reward of 2019/2020 Semester 1 from the School of Computing, National University of Singapore.
Aug 2020	I was invited to give a talk at the Department of Computer Science, Fudan University with the topic "Question Generation with Deep Reasoning"
Jul 2020	One paper accepted by ACM MM 2020: Multi-modal Cooking Workflow Construction for Food Recipes (oral presentation, acceptance rate: 27.8%).
Jul 2020	From August 2020 to July 2021, I am joining the UC Santa Barbara Natural Language Processing Group as a visiting Ph.D. student, supervised by Prof. William Wang.
Apr 2020	Two papers accepted by ACL 2020: Semantic Graphs for Generating Deep Questions, and Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen (acceptance rate: 25.2%).
Feb 2020	Our paper accepted by CVPR 2020: Hyperbolic Visual Embedding Learning for Zero-Shot Recognition (acceptance rate: 22%).
Dec 2019	A paper list on Github to summarize the recent research on neural question generation.
Nov 2019	Our paper accepted by AAAI 2020: Zero-shot Ingredient Recognition by Multi-Relational Graph Convolutional Network (acceptance rate: 20.6%).
May 2019	A survey paper on Recent Advances in Neural Question Generation.