Publications

[Google Scholar]

Taming Overconfidence in LLMs: Reward Calibration in RLHF [PDF] [Code]

Jixuan Leng, Chengsong Huang, Banghua Zhu, Jiaxin Huang
Preprint 2024.

Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning [PDF] [Code]

Chengsong Huang, Langlin Huang, Jiaxin Huang
Preprint 2024.

GOFA: A Generative One-For-All Model for Joint Graph Language Modeling [PDF]

Lecheng Kong, Jiarui Feng, Hao Liu, Chengsong Huang, Jiaxin Huang, Yixin Chen, Muhan Zhang
Preprint 2024.

Optimizing Language Model's Reasoning Abilities with Weak Supervision [PDF]

Yongqi Tong*, Sizhe Wang*, Dawei Li, Yifan Wang, Simeng Han, Zi Lin, Chengsong Huang, Jiaxin Huang, Jingbo Shang.
Preprint 2024.

Ontology Enrichment for Effective Fine-grained Entity Typing [PDF]

Siru Ouyang, Jiaxin Huang, Pranav Pillai, Yunyi Zhang, Yu Zhang, Jiawei Han.
in Proc. 2024 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD’24), Barcelona, Spain, Aug. 2024

Large Language Models Can Self-Improve [PDF]

Jiaxin Huang, Shixiang Shane Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, Jiawei Han.
in The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP'23), Singapore, Dec. 2023

Pretrained Language Representations for Text Understanding: A Weakly-Supervised Perspective”, (Conference Tutorial) [Slides]

Yu Meng, Jiaxin Huang, Yu Zhang, Yunyi Zhang, and Jiawei Han,
in Proc. 2023 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD’23), Long Beach, CA, Aug. 2023

Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning [PDF] [Code]

Yu Meng, Martin Michalski, Jiaxin Huang, Yu Zhang, Tarek Abdelzaher, Jiawei Han,
in Proc. 2023 Int. Conf. on Machine Learning (ICML’23), Honolulu, Hawaii, July 2023

Turning Web-Scale Texts to Knowledge: Transferring Pretrained Representations to Text Mining Applications (Conference Tutorial) [Slides]

Yu Meng, Jiaxin Huang, Yu Zhang, and Jiawei Han,
in Proc. 2023 The Web Conf. (WWW’23), Austin, TX, Apr. 2023

FineSum: Target-Oriented, Fine-Grained Opinion Summarization [PDF]

Suyu Ge, Jiaxin Huang, Yu Meng, and Jiawei Han,
in Proc. 2023 ACM Int. Conf. on Web Search and Data Mining (WSDM’23), Singapore, Feb. 2023

Generating Training Data with Language Models: Towards Zero-Shot Language Understanding [PDF] [Code]

Yu Meng, Jiaxin Huang, Yu Zhang, and Jiawei Han,
in Proc. 2022 Conf. on Neural Information Processing Systems (NeurIPS’22), New Orlean, LA, Nov. 2022

Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation [PDF] [Code]

Jiaxin Huang, Yu Meng and Jiawei Han,
in Proc. of 2022 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD'22), Washington, DC, Aug. 2022

Topic Discovery via Latent Space Clustering of Language Model Embeddings [PDF] [Code]

Yu Meng, Yunyi Zhang, Jiaxin Huang, Yu Zhang and Jiawei Han,
in Proc. The ACM Web Conf. 2022 (WWW'22), April 2022

Few-Shot Named Entity Recognition: An Empirical Baseline Study [PDF] [Code] [Benchmark]

Jiaxin Huang, Chunyuan Li, Krishan Subudhi, Damien Jose, Shobana Balakrishnan, Weizhu Chen, Baolin Peng, Jianfeng Gao and Jiawei Han
in Proc. of 2021 Conf. on Empirical Methods in Natural Language Processing (EMNLP'21), Nov. 2021

Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training [PDF] [Code]

Yu Meng, Yunyi Zhang, Jiaxin Huang, Xuan Wang, Yu Zhang, Heng Ji and Jiawei Han
in Proc. of 2021 Conf. on Empirical Methods in Natural Language Processing (EMNLP'21), Nov. 2021

On the Power of Pre-Trained Text Representations: Models and Applications in Text Mining (Conference Tutorial) [PDF] [Code]

Yu Meng, Jiaxin Huang, Yu Zhang, Jiawei Han
in Proc. of 2021 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD'21), Aug. 2021

Weakly-supervised Aspect-based Sentiment Analysis via Composite Aspect-sentiment Topic Embedding[PDF] [Code]

Jiaxin Huang, Yu Meng, Fang Guo, Heng Ji and Jiawei Han
in Proc. of 2020 Conf. on Empirical Methods in Natural Language Processing (EMNLP'20), Nov. 2020

Text Classification Using Label Names Only: A Language Model Self-Training Approach [PDF] [Code]

Yu Meng, Yunyi Zhang, Jiaxin Huang, Chenyan Xiong, Heng Ji, Chao Zhang and Jiawei Han
in Proc. of 2020 Conf. on Empirical Methods in Natural Language Processing (EMNLP'20), Nov. 2020

CoRel: Seed-Guided Topical Taxonomy Construction by Concept Learning and Relation Transferring [PDF]

Jiaxin Huang, Yiqing Xie, Yu Meng, Yunyi Zhang and Jiawei Han
in Proc. of 2020 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD’20), San Diego, CA, August 2020

Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding [PDF]

Yu Meng, Yunyi Zhang, Jiaxin Huang, Yu Zhang, Chao Zhang and Jiawei Han
in Proc. of 2020 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD’20), San Diego, CA, August 2020

Embedding-Driven Multi-Dimensional Topic Mining and Text Analysis (Conference tutorial)[Website & Slides]

Yu Meng, Jiaxin Huang, Jiawei Han
in Proc. of 2020 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD’20), San Diego, CA, August 2020

Minimally Supervised Categorization of Text with Metadata[PDF]

Yu Zhang, Yu Meng, Jiaxin Huang, Frank F. Xu, Xuan Wang and Jiawei Han
in Proc. 2020 ACM SIGIR Int. Conf. on Research and development in Information Retrieval (SIGIR’20), Xi’an, China, July 2020

Guiding Corpus-based Set Expansion by Auxiliary Sets Generation and Co-Expansion[PDF]

Jiaxin Huang*, Yiqing Xie*, Yu Meng, Jiaming Shen, Yunyi Zhang and Jiawei Han
in Proc. 2020 Int. World Wide Web Conf. (WWW’20), Taipei, Taiwan, Apr. 2020

Discriminative Topic Mining via Category-Name Guided Text Embedding[PDF]

Yu Meng*, Jiaxin Huang*, Guangyuan Wang, Zihan Wang, Chao Zhang, Yu Zhang and Jiawei Han
in Proc. 2020 Int. World Wide Web Conf. (WWW’20), Taipei, Taiwan, Apr. 2020

TextCube: Automated Construction and Multidimensional Exploration

Yu Meng, Jiaxin Huang, Jingbo Shang, and Jiawei Han
Conference tutorial at 2019 Int. Conf. on Very Large Data Bases (VLDB’19), Los Angeles, CA, Aug. 2019

Spherical Text Embedding [PDF]

Yu Meng, Jiaxin Huang, Guangyuan Wang, Chao Zhang, Honglei Zhuang, Lance Kaplan and Jiawei Han
in Proc. 2019 Conf. on Neural Information Processing Systems (NeurIPS’19), Vancouver, Canada, Dec. 2019

TopicMine: User-Guided Topic Mining by Category-Oriented Embedding

Yu Meng*, Jiaxin Huang*, Zihan Wang, Chenyu Fan, Guangyuan Wang, Chao Zhang, Jingbo Shang, Lance Kaplan, Jiawei Han
in Proc. of 2019 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD’19), (demo paper), Anchorage, AK, August 2019

Understanding Motivations behind Inaccurate Check-ins

Fengli Xu, Guozhen Zhang, Zhilong Chen, Jiaxin Huang, Yong Li, Diyi Yang, Ben Y. Zhao, Fanchao Meng
in Proc. of 2018 ACM CSCW Conference on Computer-Supported Cooperative Work (CSCW’2018)

Big Data Driven Mobile Traffic Understanding and Forecasting: A Time Series Approach

Fengli Xu, Yujun Lin, Jiaxin Huang, Yong Li
IEEE Transactions on Services Computing, 2016.