Postdoctoral Fellow
Stanford University
30 Million Canvas Records Reveal Widespread Sequential Bias and System-induced Surname Initial Disparity in Grading.
Jiaxin Pei, Zhihan (Helen) Wang, Jun Li
Major Revision at Management Science
Working paper available on SSRN
Best Student Paper Award🏆at EAAMO
Past presentations: CIST 2023, INFORMS 2023, EAAMO 2023
Media Coverage:
Interview with Michigan News |
Daily Mail |
ABC News |
Newsweek |
Fox News
User-Driven Value Alignment: Understanding Users’ Perceptions and Strategies for Addressing Biased and Discriminatory Statements in AI Companions
Xianzhe Fan, Qing Xiao, Xuhui Zhou, Jiaxin Pei, Maarten Sap, Zhicong Lu, Hong Shen
Arxiv
Modeling and Detecting Company Risks from News
Jiaxin Pei, Soumya Vadlamannati, Liang-Kang Huang, Daniel Preotiuc-Pietro, Xinyu Hua
The 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL'24)
Paper | Blog
Is “A Helpful Assistant” the Best Role for Large Language Models? A Systematic Evaluation of Social Roles in System Prompts
Mingqian Zheng, Jiaxin Pei and David Jurgens
Findings of the 2024 Conference on Empirical Methods on Natural Language Processing (EMNLP'24 findings)
Paper |
Github
Media Coverage:
The Markup
Aligning with Whom? Large Language Models Have Gender and Racial Biases in Subjective NLP Tasks
Huaman Sun, Jiaxin Pei, Minje Choi and David Jurgens
Paper |
Github
Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark
*Jiaxin Pei, *Minje Choi, Sagar Kumar, Chang Shu and David Jurgens (*Equal Contributions)
The 2023 Conference on Empirical Methods on Natural Language Processing (EMNLP'23)
Paper | Dataset | Github
SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research
Dimosthenis Antypas, Asahi Ushio, Francesco Barbieri, Leonardo Neves, Kiamehr Rezaee, Luis Espinosa-Anke, Jiaxin Pei, Jose Camacho-Collados
Findings of the 2023 Conference on Empirical Methods on Natural Language Processing (EMNLP'23 findings)
Paper | Dataset
When Do Annotator Demographics Matter? Measuring The Influence of Annotator Demographics with the POPQUORN Dataset
Jiaxin Pei and David Jurgens
The 17th Linguistic Annotation Workshop (LAW-XVII) @ACL 2023
Paper |
Dataset |
Annotation interface
Media Coverage:
Michigan News |
Prolific |
Digit News |
Today Headline
Exploring Linguistic Style Matching in Online Communities: The Role of Social Context and Conversation Dynamics
*Aparna Ananthasubramaniam, *Hong Chen, *Jason Yan, *Kenan Alkiek, *Jiaxin Pei, *Agrima Seth, *Lavinia Dunagan, *Minje Choi, *Benjamin Litterer and David Jurgens (*Equal Contributions)
The 1st Workshop on Social Influence in Conversations (SICon) @ACL
Best Paper Award🏆
Paper |
Github
SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysis
Jiaxin Pei, VĂtor Silva, Maarten Bos, Yozon Liu, Leonardo Neves, David Jurgens and Francesco Barbieri
The 17th International Workshop on Semantic Evaluation (SemEval'23)
Website |
Paper
🥔POTATO: The Portable Text Annotation Tool
Jiaxin Pei, Aparna Ananthasubramaniam, Xingyao Wang, Naitian Zhou, Jackson Sargent, Apostolos Dedeloudis and David Jurgens
The 2022 Conference on Empirical Methods on Natural Language Processing (EMNLP'22 demo)
Paper |
Github |
Website
Modeling Information Change in Science Communication with Semantically Matched Paraphrases
*Jiaxin Pei, *Dustin Wright, David Jurgens and Isabelle Augenstein (*Equal Contributions)
The 2022 Conference on Empirical Methods on Natural Language Processing (EMNLP'22)
Honorable Mention Award🏆 at IC2S2 2023
Paper |
Github |
Dataset |
pip install |
Annotation interface
Measuring Sentence-level and Aspect-level Uncertainty in Science Communications
Jiaxin Pei and David Jurgens
The 2021 Conference on Empirical Methods on Natural Language Processing (EMNLP'21)
Resources:
Project Website |
Paper |
Annotated Data |
Science mention data |
Model |
pip install |
Annotation interface
Media Coverage:
Poynter Media |
Michigan News |
phys.org |
ZME Science
Quantifying Intimacy in Language
Jiaxin Pei and David Jurgens
The 2020 Conference on Empirical Methods on Natural Language Processing (EMNLP'20)
Paper | Data |
Model |
pip |
demo
MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization
*Jiaxin Pei, *Canwen Xu, Hongtao Wu, Yiyu Liu and Chenliang Li (*Equal Contributions)
The 58th Annual Meeting of the Association for Computational Linguistics (ACL'20)
Paper | Data |
Model
Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders
Yu Duan, Canwen Xu, Jiaxin Pei, Jialong Han and Chenliang Li
The 58th Annual Meeting of the Association for Computational Linguistics (ACL'20)
Paper | Model
DLocRL: A Deep Learning Pipeline for Fine-Grained Location Recognition and Linking in Tweets
with Relevant Information
Canwen Xu, Jing Li, Xiangyang Luo, Jiaxin Pei, Chenliang Li, Donghong Ji
The Web Conference 2019 (WWW'19)
Paper
S2SPMN:A Simple and Effective Framework for Response Generation
with Relevant Information
Jiaxin Pei and Chenliang Li
The 2018 Conference on Empirical Methods on Natural Language Processing (EMNLP'18)
Paper
Targeted Sentiment Analysis: A Data-Driven Categorization
Jiaxin Pei, Aixin Sun, Chenliang Li
Arxiv Link
SUM: Suboptimal Unitary Multi-task Learning Framework for
Spatiotemporal Data Prediction
Qichen Li, Jiaxin Pei, Jianding Zhang, Bo Han
Arxiv Link