Fan Yin (银帆)
Hi, I am a final-year PhD student in the Computer Science department at University of California, Los Angeles (UCLA), advised by Prof.Kai-Wei Chang. Preivously, I received my B.S. degree in Computer Science from Peking University in 2020, where I worked with Prof. Xiaojun Wan. My research interests lie in 1) reliability, robustness, and interpretation for NLP systems, with a recent focus on helping build more human trust and understanding on LLMs through estimating and calibrating model predictions; 2) aligning LLMs from data perspective, with a recent focus on interpretablee methods for data synthesizing and curation.
Email  / 
linkedin  / 
Github  / 
CV  / 
Google Scholar
|
|
Education
Ph.D.          Sep. 2020 - Present
                       University of California Los Angeles (UCLA), Los Angeles, CA, U.S.
                       Ph.D. student in Computer Science
|
B.S.              Sep. 2016 - June 2020
                       Peking University (PKU), Beijing, China.
                       B.S. in Computer Science
|
|
Intern Experience
-
Oct 2024 -- Dec 2024, Google LLC, Kirkland
Student Researcher. Manager: Hamid Palangi
-
Jun 2024 -- Sep 2024, Salesforce, Palo Alto
Research Intern. Mentors: Philippe Laben and Becky Xiangyu Peng. Manager: Jason WU.
-
Jun 2023 -- Sep 2023, Amazon AWS, Santa Clara
Applied Scientist Intern. Mentors: He He and Samson Tan. Manager: Aditya Rawal.
-
Jun 2022 -- Sep 2022, Salesforce Research, Palo Alto
Research Intern. Mentors: Jesse Vig and Philippe Laban. Manager: Jason Wu.
-
Jun 2021 -- Sep 2021, Amazon AWS, remote
Applied Scientist Intern. Mentor: Prof. He He
-
Jan.2019 -- Jun.2019, Sep.2019 -- Dec.2019, ShannonAI , Beijing, China
Software Engineer Intern, advised by Jiwei Li
-
Jun.2019 -- Sep.2019, University of California, Los Angeles (UCLA) , CA, US
Reseach Intern, advised by Prof. Kai-Wei Chang
|
BingoGuard: LLM Content Moderation Tools with Risk Levels
Fan Yin, Philippe Laban, Xiangyu Peng, Yilun Zhou, Yixin Mao, Vaibhav Vats, Linnea Ross, Divyansh Agarwal, Caiming Xiong, Chien-Sheng Wu
In submission
[ paper | code ]
|
Alignment Data Curation with Influence Function
|
Data Synthesize and Curation for Process-supervison Reward Modeling of Tool-use Agent
|
Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller
Min Cai, Yuchen Zhang, Shichang Zhang, Fan Yin, Difan Zou, Yisong Yue, Ziniu Hu
arxiv
[ paper | code ]
|
Evaluating Human Alignment and Model Faithfulness of LLM Rationale
Mohsen Fayyaz, Fan Yin, Jiao Sun, Nanyun Peng
arxiv
[ paper | code ]
|
Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation
Di Wu, Jia-Chen Gu, Fan Yin, Nanyun Peng, Kai-Wei Chang
EMNLP 2024
[ paper | code ]
|
Enhancing Large Vision Language Models with Self-Training on Image Comprehension
Yihe Deng, Pan Lu, Fan Yin, Ziniu Hu, Sheng Shen, James Zou, Kai-Wei Chang, Wei Wang
NeurIPS 2024
[ paper | code ]
|
Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension
Fan Yin, Jayanth Srinivasa, Kai-Wei Chang
ICML 2024
[ paper | code ]
|
Prompt-Driven LLM Safeguarding via Directed Representation Optimization
Chujie Zheng, Fan Yin, Hao Zhou, Fandong Meng, Jie Zhou, Kai-Wei Chang, Minlie Huang, Nanyun Peng
ICML 2024
[ paper | code ]
|
Red Teaming Language Model Detectors with Language Models
Zhouxing Shi*, Yihan Wang*, Fan Yin*, Xiangning Chen, Kai-Wei Chang, Cho-Jui Hsieh
TACL, equal contribution, ordered alphabetically
[ paper | code ]
|
Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks
Po-Nien Kung, Fan Yin, Di Wu, Kai-Wei Chang, Nanyun Peng
EMNLP 2023
[ paper | code ]
|
Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation
Da Yin*, Xiao Liu*, Fan Yin*, Ming Zhong*, Hritik Bansal, Jiawei Han, Kai-Wei Chang
EMNLP 2023, equal contribution
[ paper | code ]
|
Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning
Fan Yin, Jesse Vig, Philippe Laban, Shafiq Joty, Caiming Xiong, Chien-Sheng Jason Wu
ACL 2023
[ paper | code ]
|
Chenghao Yang, Fan Yin, He He, Kai-Wei Chang, Xiaofei Ma, Bing Xiang
ACL 2023
[ paper | code ]
|
Hritik Bansal, Nishad Singhi, Yu Yang, Fan Yin, Aditya Grover, Kai-Wei Chang
ICCV 2023, Oral | Best Paper Award at Trustworthy and Reliable Large-Scale ML@ICLR 2023
[ paper | code ]
|
Fan Yin, Yao Li, Cho-Jui Hsieh, Kai-Wei Chang
EMNLP 2022
[ paper | code ]
|
Fan Yin, Zhouxing Shi, Cho-Jui Hsieh, Kai-Wei Chang
ACL 2022
[ paper | code ]
|
Fan Yin, Quanyu Long, Tao Meng, Kai-Wei Chang
ACL 2020
[ paper | code ]
|
Xiaoya Li*, Fan Yin*, Zijun Sun, Xiayu Li, Arianna Yuan, Duo Chai, Mingxin Zhou, Jiwei Li
ACL 2019, equal contribution
[ paper | code ]
|
Yuxian Meng, Wei Wu, Fei Wang, Xiaoya Li, Ping Nie, Fan Yin, Muyu Li, Qinghong Han, Xiaofei Sun, Jiwei Li
NeurIPS 2019
[ paper | code ]
|
Academic Services
-
Journal/Conference Reviewer: NeurIPS 2022, ACL 2022, NAACL 2022, NAACL Student Research Workshop 2022
|
Teaching
-
Teaching Associate position, UCLA CS M146, Introduction to Machine learning, Fall 2022, with Prof. Kai-Wei Chang
-
Teaching Assistant, UCLA CS M146, Introduction to Machine learning, Fall 2021, with Prof. Kai-Wei Chang
-
Teaching Assistant, UCLA CS M146, Introduction to Machine learning, Winter 2022, with Prof. Sriram
Sankararaman
-
Teaching Assistant, UCLA CS M146, Introduction to Machine learning, Spring 2022, with Prof. Aditya
Grover
|
Awards
-
Excellent Graduate, Peking University, 2020.
-
Merit Student, Peking University, 2019.
|
|