I am a first-year PhD student at University of Illinois Urbana-Champaign, advised by Prof. Hao Peng and working closely with Prof. Heng Ji.
Previously, I was fortunate to work with Prof. Zhiyuan Liu at THUNLP.
My research pursues scalable oversight for LLM (self-)evolution. To this end, I work on:
- Scalable data synthesis techniques that overcome LLM limitations [UltraFeedback,UltraInteract].
- Scalable supervision methods that provide immediate feedback for LLMs [Eurus-RM].
- Scalable training algorithms that efficiently incorporate new data and supervision signals [Ongoing].
🔥 News
- 2024.09: NCA has been accepted to NeurIPS and CPO has been accepted to EMNLP.
- 2024.05: UltraFeedback and CodeAct have been accepted to ICML. UltraFeedback has been perhaps the most popular preference dataset since its release – it has powered 1k+ models on HuggingFace, ranking in the top 5 on HF! CodeAct has also been included as a major part of the star project OpenHands!
- 2024.04: We release Eurus, a suite of open-source LLM reasoning generalists! Eurus models are powered by UltraInteract preference trees, please check out!
- 2024.01: CRAFT and MINT have been accepted to ICLR.
- 2023.10:One paper accepted to EMNLP.
- 2023.10: We release UltraFeedback, the largest non-community annotated preference dataset, based on which we train UltraRM-13B, the best open-source reward model that is on par with LLaMA-2-70B-Helpfulness RM.
📝 Publications
* denotes equal contribution
-
Advancing LLM Reasoning Generalists with Preference Trees [Paper]
Lifan Yuan*, Ganqu Cui*, Hanbin Wang*, Ning Ding, Xingyao Wang, Jia Deng, Boji Shan, Huimin Chen, Ruobing Xie, Yankai Lin, Zhenghao Liu, Bowen Zhou, Hao Peng, Zhiyuan Liu, Maosong Sun.
ICML 2024 Workshop On AI4Math -
UltraFeedback: Boosting Language Models with High-quality Feedback [Paper]
Ganqu Cui*, Lifan Yuan*, Ning Ding, Guanming Yao, Wei Zhu, Yuan Ni, Guotong Xie, Zhiyuan Liu, Maosong Sun.
ICML 2024 -
CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets [Paper]
Lifan Yuan*, Yangyi Chen*, Xingyao Wang, Yi R. Fung, Hao Peng, Heng Ji.
ICLR 2024 -
Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations [Paper]
Lifan Yuan, Yangyi Chen, Ganqu Cui, Hongcheng Gao, Fangyuan Zou, Xingyi Cheng, Heng Ji, Zhiyuan Liu, Maosong Sun.
NeurIPS 2023 (Datasets and Benchmarks Track) -
A Close Look into the Calibration of Pre-trained Language Models [Paper]
Yangyi Chen*, Lifan Yuan*, Ganqu Cui, Zhiyuan Liu, Heng Ji.
ACL 2023
-
Advancing LLM Reasoning Generalists with Preference Trees [Paper]
Lifan Yuan*, Ganqu Cui*, Hanbin Wang*, Ning Ding, Xingyao Wang, Jia Deng, Boji Shan, Huimin Chen, Ruobing Xie, Yankai Lin, Zhenghao Liu, Bowen Zhou, Hao Peng, Zhiyuan Liu, Maosong Sun. -
Prudent Silence or Foolish Babble? Examining Large Language Models' Responses to the Unknown [Paper]
Genglin Liu, Xingyao Wang, Lifan Yuan, Yangyi Chen, Hao Peng. -
Zero-Shot Generalization during Instruction Tuning: Insights from Similarity and Granularity [Paper]
Bingxiang He*, Ning Ding*, Cheng Qian*, Jia Deng, Ganqu Cui, Lifan Yuan, Huan-ang Gao, Huimin Chen, Zhiyuan Liu, Maosong Sun. -
Noise Contrastive Alignment of Language Models with Explicit Rewards [Paper]
Huayu Chen, Guande He, Lifan Yuan, Ganqu Cui, Hang Su, Jun Zhu.
NeurIPS -
Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment [Paper]
Yiju Guo*, Ganqu Cui*, Lifan Yuan, Ning Ding, Jiexin Wang, Huimin Chen, Bowen Sun, Ruobing Xie, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun.
EMNLP -
UltraFeedback: Boosting Language Models with High-quality Feedback [Paper]
Ganqu Cui*, Lifan Yuan*, Ning Ding, Guanming Yao, Wei Zhu, Yuan Ni, Guotong Xie, Zhiyuan Liu, Maosong Sun.
ICML -
Executable Code Actions Elicit Better LLM Agents [Paper]
Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, and Heng Ji.
ICML -
CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets [Paper]
Lifan Yuan*, Yangyi Chen*, Xingyao Wang, Yi R. Fung, Hao Peng, Heng Ji.
ICLR -
MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback [Paper]
Xingyao Wang*, Zihan Wang*, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng, Heng Ji.
ICLR -
Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT [Paper]
Biru Zhu, Lifan Yuan, Ganqu Cui, Yangyi Chen, Chong Fu, Bingxiang He, Yangdong Deng, Zhiyuan Liu, Maosong Sun, Ming Gu.
EMNLP -
Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations [Paper]
Lifan Yuan, Yangyi Chen, Ganqu Cui, Hongcheng Gao, Fangyuan Zou, Xingyi Cheng, Heng Ji, Zhiyuan Liu, Maosong Sun.
NeurIPS (Datasets and Benchmarks Track) -
Removing Backdoors in Pre-trained Models by Regularized Continual Pre-training [Paper]
Biru Zhu*, Ganqu Cui*, Yangyi Chen, Yujia Qin, Lifan Yuan, Chong Fu, Yangdong Deng, Zhiyuan Liu, Maosong Sun, Ming Gu.
TACL -
A Close Look into the Calibration of Pre-trained Language Models [Paper]
Yangyi Chen*, Lifan Yuan*, Ganqu Cui, Zhiyuan Liu, Heng Ji.
ACL -
Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework [Paper]
Lifan Yuan*, Yichi Zhang*, Yangyi Chen, Wei Wei.
ACL (Findings) -
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework [Paper]
Yangyi Chen*, Hongcheng Gao*, Ganqu Cui*, Lifan Yuan, Dehan Kong, Hanlu Wu, Ning Shi, Bo Yuan, Longtao Huang, Hui Xue, Zhiyuan Liu, Maosong Sun, Heng Ji.
ACL (Findings) -
A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks [Paper]
Ganqu Cui*, Lifan Yuan*, Bingxiang He, Yangyi Chen, Zhiyuan Liu, Maosong Sun.
NeurIPS (Datasets and Benchmarks Track) (Spotlight) -
FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition [Paper]
Lifan Yuan*, Linyi Yang*, Leyang Cui, Wenyang Gao, Yue Zhang.
COLING (Oral) -
Deep Clustering and Visualization for End-to-End High-Dimensional Data Analysis [Paper]
Lirong Wu*, Lifan Yuan*, Guojiang Zhao, Haitao Lin, Stan Z. Li.
IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Preprints
2024
2023
2022
📄 Academic Services
2025: ICLR.
2024: ICLR, ICML, NeurIPS, ARR.
2023: ACL, NeurIPS, EMNLP, ARR.
2022: NeurIPS, EMNLP, ARR.