Welcome to Lemao’s Homepage
I am currently a principal researcher at Tencent, working on large language models, natural language processing, machine translation and their related topics. I can be reached through NAME at gmail dot com (NAME=lemaoliu).
More about me
I am from Yugan in Jiangxi Provice, which is a small yet beautiful county near Poyang Lake, the largest freshwater lake in China. I earned my Ph.D. degree at Harbin Institute of Technology (HIT) in Oct. 2013, under the instructions of Prof. Tiejun Zhao at HIT and Dr. Taro Watanabe at NICT. After that, I was a postdoc researcher at the City University of New York, working with Prof. Liang Huang; and then I was a researcher at NICT Japan between Sept. 2014 and March 2017.
News
- 05/2024: Six papers accepted by ACL 2024.
- 10/2023: Eight papers accepted by EMNLP 2023.
- 09/2023: Three papers accepted by NeurIPS 2023.
- 05/2023: Six papers accepted by ACL 2023.
- 10/2022: Four papers accepted by EMNLP 2022.
- 06/2022: Area Chair at EMNLP 2022.
- 04/2022: Area Chair at NLPCC 2022.
- 03/2022: Tutorials accepted by IJCAI 2022 and SIGIR 2022.
- 02/2022: Five papers accepted by ACL 2022 and one paper by NAACL 2022.
- 11/2021: Four papers accepted by EMNLP 2021.
- 07/2021: Outstanding Paper Award at ACL 2021.
- 05/2021: Seven papers accepted by ACL 2021.
- 07/2020: Best Demo Award at CCL 2020.
- 04/2020: Two papers accepted by ACL 2020.
- 02/2020: One paper accepted by JAIR.
Professional Activities
- ACL Rolling Review: (Senior) Area Chair.
- EMNLP 2024: Area Chair (Industry Track).
- EMNLP 2022: Area Chair.
- IJCAI 2021: Senior Program Committee.
- EMNLP 2020 (Findings): Publication Chair.
- Computational Linguistics and Transaction of ACL: Standing Reviewers.
Publications
For full publication list, please check [Google Scholar]
Recent Research Related to LLM and RAG
Large Language Models (LLM)
- Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, Longyue Wang, Anh Tuan Luu, Wei Bi, Freda Shi, Shuming Shi. Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models. Preprints in 2023. (700+ citations)
- Guoxin Yu, Lemao Liu, Mo Yu, Yue Yu, Xiang Ao. Rethinking the Evaluation of In-Context Learning for LLMs. Proceedings of EMNLP 2024.
- Tsz Ting Chung, Leyang Cui, Lemao Liu, Xinting Huang, Shuming Shi, Dit-Yan Yeung. Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability. Proceedings of EMNLP 2024: Findings.
- Tingchen Fu, Lemao Liu, Deng Cai, Guoping Huang, Shuming Shi, Rui Yan. The Reasonableness Behind Unreasonable Translation Capability of Large Language Model. Proceedings of ICLR 2024.
- Qihang Ai, Jiafan Li, Jincheng Dai, Jianwu Zhou, Lemao Liu, Haiyun Jiang, Shuming Shi. Advancement in Graph Understanding: A Multimodal Benchmark and Fine-Tuning of Vision-Language Models. Proceedings of ACL 2024.
- Xueliang Zhao, Xinting Huang, Tingchen Fu, Qintong Li, Shansan Gong, Lemao Liu, Wei Bi, Lingpeng Kong. BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models. Proceedings of ACL 2024: Findings.
- Huayang Li, Siheng Li, Deng Cai, Longyue Wang, Lemao Liu, Taro Watanabe, Yujiu Yang, Shuming Shi. TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild. Proceedings of ACL 2024: Findings.
- Tingchen Fu, Deng Cai, Lemao Liu, Shuming Shi, Rui Yan. Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction. Proceedings of ACL 2024: Findings.
- Huayang Li, Tian Lan, Zihao Fu, Deng Cai, Lemao Liu, Nigel Collier, Taro Watanabe, Yixuan Su. Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective. Proceedings of NeurIPS 2023.
- Huan Ma, Changqing Zhang, Yatao Bian, Lemao Liu, Zhirui Zhang, Peilin Zhao, Shu Zhang, Huazhu Fu, Qinghua Hu, Bingzhe Wu. Fairness-guided Few-shot Prompting for Large Language Models. Proceedings of NeurIPS 2023.
Retrieval Augmented Generation (RAG)
- Huayang Li, Yixuan Su, Deng Cai, Yan Wang, and Lemao Liu. A survey on retrieval-augmented text generation. Preprints in 2021. (100+ citations in 2024)
- Huayang Li, Deng Cai, Zhi Qu, Qu Cui, Hidetaka Kamigaito, Lemao Liu, Taro Watanabe. Cross-lingual Contextualized Phrase Retrieval. Proceedings of EMNLP 2024: Findings.
- Xin Cheng, Di Luo, Xiuying Chen, Lemao Liu, Dongyan Zhao, Rui Yan. Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory. Proceedings of NeurIPS 2023.
- Hongkun Hao, Guoping Huang, Lemao Liu, Zhirui Zhang, Shuming Shi, Rui Wang. Rethinking Translation Memory Augmented Neural Machine Translation. Proceedings of ACL 2023: Findings.
- Xin Cheng, Shen Gao, Lemao Liu, Dongyan Zhao and Rui Yan. Neural Machine Translation with Contrastive Translation Memories. Proceedings of EMNLP 2022.
- Deng Cai, Yan Wang, Huayang Li, Wai Lam and Lemao Liu. Neural Machine Translation with Monolingual Translation Memory. Proceedings of ACL 2021. (Outstanding Paper Award) [code]
- Qiuxiang He, Guoping Huang, Qu Cui, Li Li and Lemao Liu. Fast and Accurate Neural Machine Translation with Translation Memory. Proceedings of ACL 2021.
- Mengzhou Xia, Guoping Huang, Lemao Liu, and Shuming Shi. Graph-based Translation Memory for Neural Machine Translation. Proceedings of AAAI 2019.
Collaborators
Interns/Students
It is my pleasure and great honor to work with the following excellent students.
Current Interns/Students
- Xueliang Zhao (Tencent Rhino-Bird Scholar, master student at Peking, 08/2021 - )
- Hongkun Hao (Undergraduate at Shanghai Jiaotong Univ., 12/2021)
- Wei Shao (CityU of HK, 12/2021 - )
Past Interns/Students
- Yubin Ruan (M.S. at HIT, 06/2021 - 02/2022, 1 NAACL)
- Jiahao Xu (Phd student at NTU, 08/2021 - 02/2022, 1 NAACL + 2 EMNLP)
- Yanling Xiao (Co-advised with Guoping, master student at Nanjing Univ., 07/2020 - 02/2022, 1 ACL)
- Yibin Liu (engineering intern, master student at Peking Shenzhen, 11/2020 - 02/2022, 1 EMNLP)
- Qiuxiang He (Co-advised with Guoping, Southwest Univ., 07/2020 - 12/2021, 1 ACL)
- Jiannan Xiang (master student at USTC, 05/2020 - 2021/09, now phd at UCSD; 3 ACL)
- Zexin Lu (Tencent Rhino-Bird Scholar, phd student at Poly HK, 05/2021 - 12/2021, 1 ACL)
- Guanlin Li (phd student at HIT, 12/2017 - 2021/02; now Researcher at JD, 2 ACL + 1 EMNLP + 1 NAACL + 2 TASLP)
- Zhangming Chan (Tencent Rhino-Bird Scholar, master from Peking Univ., 05/2020 - 2021/01, 1 ACL)
- Jing Qian (phd student at UCSB, 06/2020 - 09/2020; now Researcher at Microsoft 1 EMNLP)
- Honglin Han (engineering intern, undergraduate student at HIT, 04/2020 - 09/2020)
- Jierui Li (undergraduate student at UESTC, now phd student at UT Austin, 11/2019 - 06/2020, 1 ACL)
- Runze Nie (engineering intern, graduate student at Univ. Melbourne, 12/2019 - 03/2020)
- Tianxiang Zhao (Co-advised with Guoping, graduate student at USTC, 01/2019 - 06/2019; now phd student at PSU, 1 AAAI)
- Qian Wang (Co-advised with Guoping, master student at IA CAS, 07/2018 - 12/2019, 1 AACL)
- Xintong Li (phd student at CUHK, 07/2017 - 05/2019; now senior researcher at Apple, 2 ACL + 2 NAACL + 1 TASLP)
- Mengzhou Xia (Co-advised with Guoping, undergraduate student at Fudan, 04/2018 - 08/2018; now phd student at Princeton, 1 AAAI)
- Huayang Li (Co-adivsed with Guoping, undergraduate student at Central China Normal Univ., 07/2017 - 05/2018; now phd at NAIST, 1 TASLP)
- Yu Liu (phd student at HIT, 04/2018 - 11/2018)
- Lianhui Qin (graduate student at SHJT, 07/2017 - 09/2017; now Ass. Prof. at UCSD, 1 ACL)
- Kehai Chen (phd student at HIT, 10/2017 - 03/2017; now Prof. at HIT, 2 EMNLP + 1 AAAI + 2 TASLP)
- Chunpeng Ma (phd student at HIT, 10/2015 - 03/2016; Now researcher at Fujitsu., 1 AAAI)
Visitors
- Conghui Zhu (Tencent Rhino-Bird Visiting Prof. from HIT, 06/2019 - 01/2020)
Colleagues
- Eiichiro Sumita, Masao Utiyama, Andrew Finch, Akihiro Tamura, Atsushi Fujita, Rui Wang, Kehai Chen, Xugang Lu, Peng Shen, Guoping Huang, Shuming Shi etc.