| CV | Google Scholar | Github |

I am a fifth-year Ph.D. student at Wangxuan Institute of Computer Technology, Peking University, advised by Prof. Yansong Feng and Prof. Dongyan Zhao . My research interests are in document-level information extraction and adapting general LLMs into a specific domain or modality.

• [Dec. 2023] We have succeeded to train a LLM from scratch! It could process text with up to 128K. Coming soon
• [Oct. 2023] We have built a unified language-vision pretraining framework, and our model LaVIT is available now!
• [Oct. 2023] Three papers are accepted in EMNLP 2023 !
• [May. 2023] We are building a domain-specific LLMs, Lawyer LLaMA !
• [May. 2023] Our paper of proposing a unified framework for event temporal RE is accepted in ACL 2023
---- show more ----
• [Oct. 2022] Our paper of investigating whether charge prediction models learn legal knowledge is accepted in EMNLP 2022
• [May. 2022] I'm awarded with President Scholarship! It is a great hornor for a Ph.D. student in Peking University.
• [Feb. 2022] Our paper on analyzing Document RE Dataset, DocRED, got accepted by ACL 2022.
• [Apr. 2021] Our paper on analyzing Document RE got accepted by ACL 2022

Lawyer LLaMA: Enhancing LLMs with Legal Knowledge (Under Review)
Quzhe Huang, Mingxu Tao, Zhenwei An, Chen Zhang, Cong Jiang, Zhibin Chen, Zirui Wu and Yansong Feng

We have designed a framework to adapt a general LLM into a specific domain, and built a legal model, Lawyer LLaMA based on the framework.

More than Classification: A Unified Framework for Event Temporal Relation Extraction (ACL 23)
Quzhe Huang, Yutong Hu, Shengqi Zhu, Yansong Feng, Chang Liu, Dongyan Zhao

Determining the temporal relation between events based on their start and end time points, instead of treating this problem as a simple classification task.

Do Charge Prediction Models Learn Legal Theory? (Findings of EMNLP 22)
Zhenwei An*, Quzhe Huang*, Cong Jiang, Yansong Feng, Dongyan Zhao

An empirical study of whether charge prediction models make judgments corresponds to the decision logic of human judges.

Rethinking Task-Specific Knowledge Distillation: Contextualized Corpu (EMNLP 22)
Chang Liu, Chongyang Tao, Jianxin Liang, Tao Shen, Jiazhan Feng, Quzhe Huang, Dongyan Zhao

Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED (ACL 22)
Quzhe Huang, Shibo Hao, Yuan Ye, Shengqi Zhu, Yansong Feng, Dongyan Zhao

An analysis of recommend-revise annotation scheme, where existing models or knowledge bases are used to recommend candidate instances and annotators revise the recommendations. We find that in the revision stage, annotators cannot supplement adequate missing instances, which might cause bias in the constructed dataset and the models trained on the new data

Knowledge-enhanced Iterative Instruction Generation and Reasoning for Knowledge Base Question Answering (NLPCC 22)
Haowei Du, Quzhe Huang, Chen Zhang, Dongyan Zhao

Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction (ACL 21)
Quzhe Huang, Shengqi Zhu, Yansong Feng, Yuan Ye, Yuxuan Lai, Dongyan Zhao

Empirically showed that determining the relation between entities in long texts only requires limited evidence, and proposed a method based on co-reference and multi-hop reasoning to select evidence sentences for document-level RE.

Exploring Distantly-Labeled Rationales in Neural Network Models (ACL 21)
Quzhe Huang, Shengqi Zhu, Yansong Feng, Dongyan Zhao

Proposed a method to prevent the model from ignoring the potential important non-rationale words and not distinguishing the importance of different rationale words, when incorporating human ratio

Why Machine Reading Comprehension Models Learn Shortcuts? (Findings of ACL 21)
Yuxuan Lai, Chen Zhang, Yansong Feng, Quzhe Huang, Dongyan Zhao

An Investigation of the reason why machine reading comprehension models learn shortcuts. We find that it is due to the larger proportion of shortcut questions in training data.

Towards Context-Aware Code Comment Generation (Findings of EMNLP 20)
Xiaohan Yu, Quzhe Huang, Zheng Wang, Yansong Feng, Dongyan Zhao

• ACL Rollings, area chair, 2023.10
• ACL Rollings, reviewer, since 2021.9
• ACL, reviewer, 2022,2023
• EMNLP, reviewer, 2022,2023
• COLING, reviewer, 2022,2023
• EACL, reviewer, 2023
• AAAI, reviewer, 2023

• President Scholarship, Peking University, 2022
• Uniqlo Scholarship, Peking University, 2017
• Panasonic Scholarship, Peking University, 2016

Wangxuan Institute of Computer Technology, Peking University
No. 128 Zhongguancun North Street,
Haidian District, Beijing, 100871
huangquzhe@pku.edu.cn

Website design: ✩ ✩