I am a final-year PhD student in Computer Science at UCLA advised by Prof. Kai-Wei Chang, working in UCLANLP lab. I was awarded Amazon PhD Fellowship in 2023. I previously interned at Microsoft Research, AI2 Mosaic, and Amazon Alexa AI.

My research interest is building generalizable and inclusive language processing models that can be applied across applications and environments. I particularly focus on empowering stronger reasoning and planning ability of LLM agents/reasoners, and enhancing cross-region and cross-task generalizability.

I completed my bachelor's at Peking University, where I worked with Prof. Xiaojun Wan and Prof. Baobao Chang.

I'm actively looking for postdoc and industry research scientist position in 2025. Feel free to reach out if you're interested!.

Publications


LLMs as General-Purpose Simulators For Agent Training
In Progress
Guiding Through Complexity: What Makes Good Supervision for Hard Reasoning Tasks?
Xuan He*, Da Yin*, Nanyun Peng
(Equal Contribution)
In Submission
Q* Agent: Optimizing Language Agents with Q-Guided Exploration
Zongyu Lin*, Yao Tang*, Da Yin*, Stuart X. Yao, Ziniu Hu, Yizhou Sun, Kai-Wei Chang
In Submission
SafeWorld: Geo-Diverse Safety Alignment
Da Yin*, Haoyi Qiu*, Kung-Hsiang Huang, Kai-Wei Chang, Nanyun Peng
(Equal Contribution)
NeurIPS 2024
[ paper | code ]
OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation
Zilong Wang, Yuedong Cui, Li Zhong, Zimin Zhang, Da Yin, Bill Yuchen Lin, Jingbo Shang
Arxiv Preprint
[ paper | code ]
Consent in Crisis: The Rapid Decline of the AI Data Commons
Shayne Longpre, Robert Mahari, Ariel Lee, Campbell Lund, Hamidah Oderinwale, William Brannon, Nayan Saxena, Naana Obeng-Marnu, Tobin South, Cole Hunter, Kevin Klyman, Christopher Klamm, Hailey Schoelkopf, Nikhil Singh, Manuel Cherep, Ahmad Anis, An Dinh, Caroline Chitongo, Da Yin, Damien Sileo, Deividas Mataciunas, Diganta Misra, Emad Alghamdi, Enrico Shippole, Jianguo Zhang, Joanna Materzynska, Kun Qian, Kush Tiwary, Lester Miranda, Manan Dey, Minnie Liang, Mohammed Hamdy, Niklas Muennighoff, Seonghyeon Ye, Seungone Kim, Shrestha Mohanty, Vipul Gupta, Vivek Sharma, Vu Minh Chien, Xuhui Zhou, Yizhi Li, Caiming Xiong, Luis Villa, Stella Biderman, Hanlin Li, Daphne Ippolito, Sara Hooker, Jad Kabbara, Sandy Pentland
NeurIPS 2024 Dataset and Benchmark Track
Featured by New York Times
[ paper | code | Project Page ]
🪄 Agent Lumos: Unified and Modular Training for Open-Source Language Agents
Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, Bill Yuchen Lin
ACL 2024
Featured by Marktechpost
[ paper | code GitHub Repo stars | Project Page | Data & Models | Twitter ]
Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
Yifan Song, Da Yin, Xiang Yue, Jie Huang, Sujian Li, Bill Yuchen Lin
ACL 2024
[ paper | code | Twitter ]
KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation
Di Wu, Da Yin, Kai-Wei Chang
ACL 2024 Findings
[ 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
(Equal Contribution)
EMNLP 2023
[ paper | code GitHub Repo stars | Project Page | Twitter ]
LEAF: Linguistically Enhanced Event Temporal Relation Framework
Stanley Lim, Da Yin, Nanyun Peng
Pan-DL workshop @ EMNLP 2023 (Pattern-based Approaches to NLP in the Age of Deep Learning)
🏆 Best Paper Award
[ paper ]
The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code
Xiao Liu, Da Yin, Chen Zhang, Yansong Feng, Dongyan Zhao
ACL 2023 Findings
[ paper | code ]
GIVL: Improving Geographical Inclusivity of Vision-Language Models with Pre-Training Methods
Da Yin, Feng Gao, Govind Thattai, Michael Johnston, Kai-Wei Chang
CVPR 2023
[ paper | code ]
GeoMLAMA: Geo-Diverse Commonsense Probing on Multilingual Pre-Trained Language Models
Da Yin, Hritik Bansal, Masoud Monajatipoor, Liunian Harold Li, Kai-Wei Chang
EMNLP 2022 (Oral, 175/4100≈4.3%)
[ paper | code ]
How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?
Hritik Bansal*, Da Yin*, Masoud Monajatipoor, Kai-Wei Chang
(Equal Contribution)
EMNLP 2022 (Oral, 175/4100≈4.3%)
[ paper | code ]
Towards a Unified Multi-Dimensional Evaluator for Text Generation
Ming Zhong, Yang Liu, Da Yin, Yuning Mao, Yizhu Jiao, Pengfei Liu, Chenguang Zhu, Heng Ji, Jiawei Han
EMNLP 2022 (Oral, 175/4100≈4.3%)
[ paper | code GitHub Repo stars]
Things not Written in Text: Exploring Spatial Commonsense from Visual Signals
Xiao Liu, Da Yin, Yansong Feng, Dongyan Zhao
ACL 2022
[ paper | code ]
A Survey of Knowledge-Intensive NLP with Pre-Trained Language Models
Da Yin, Li Dong, Hao Cheng, Xiaodong Liu, Kai-Wei Chang, Furu Wei, Jianfeng Gao
Presented at Spa-NLP workshop @ ACL 2022 (Semiparametric Methods in NLP)
[ paper ]
Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning
Da Yin, Liunian Harold Li, Ziniu Hu, Nanyun Peng, Kai-Wei Chang
EMNLP 2021 (Oral, 315/3600≈8.8%)
[ paper | code | Project Page | Slides ]
Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis
Xiao Liu*, Da Yin*, Yansong Feng, Yuting Wu, Dongyan Zhao
(Equal Contribution)
NAACL 2021 (Oral)
[ paper | code ]
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
Ming Zhong*, Da Yin*, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Hassan Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir Radev
(Equal Contribution)
NAACL 2021 (Oral)
[ paper | code GitHub Repo stars]
SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics
Da Yin, Tao Meng, Kai-Wei Chang
ACL 2020
[ paper | code ]
What Does BERT with Vision Look At?
Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang
ACL 2020
[ paper | code ]
VisualBERT: A Simple and Performant Baseline for Vision and Language
Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, Kai-Wei Chang
Arxiv Preprint
[ paper | code GitHub Repo stars]
Interactive Multi-Grained Joint Model for Targeted Sentiment Analysis
Da Yin*, Xiao Liu*, Xiaojun Wan
(Equal Contribution)
CIKM 2019
[ paper ]
A Soft Label Strategy for Target-Level Sentiment Classification
Da Yin, Xiao Liu, Xiuyu Wu, Baobao Chang
WASSA workshop @ NAACL 2019 (Computational Approaches to Subjectivity, Sentiment and Social Media Analysis)
[ paper ]