LidongBing-photo

Lidong Bing (邴立东)

Head of the Language Technology Lab [GitHub, HuggingFace, Zhihu, Weibo]
DAMO Academy, Alibaba Group
Office: Xixi Campus C, Hangzhou, China AND 51 Bras Basah Rd, Singapore
Contact: l.bing [at] alibaba-inc.com AND binglidong [at] gmail.com

Biography

Lidong Bing is the Head of the Language Technology Lab at DAMO Academy of Alibaba Group. He received a Ph.D. from The Chinese University of Hong Kong and was a postdoc research fellow at Carnegie Mellon University. His research interests include large language models, vision-language models, and various low-resource and multilingual NLP problems. Currently, he serves as an Action Editor for Transactions of the Association for Computational Linguistics (TACL) and ACL Rolling Review (ARR), Area Chair for AI conferences, and Associate Editor for AI journals.

The NLP techniques developed by the lab served many business scenarios of Alibaba and its globalization strategy. Current projects that the lab is focusing on include SeaLLMs ([tech memo] [demo] [paper]), a family of language models optimized for Southeast Asian (SEA) languages, and Video-LLaMA ( [code] [demo] [paper]), an instruction-tuned audio-visual language model.

News/Event

Upcoming events:

  • July 31, 2024. Lidong will deliver a Keynote Address on "Bridging the Digital Divide: Strategies for Inclusive Digital Transformation" during the Mekong Forum 2024 on July 31 – August 1, 2024, at Pullman Khon Kaen Raja Orchid, Khon Kaen Province, Thailand.
  • August 11, 2024. We will present our SeaLLMs at ACL 2024, Bangkok, Thailand.

News:

  • July 10, 2024. Delivered a keynote speech on our SeaLLMs at Indonesia AI Conference 2024.
  • July 5, 2024. Award ceremony for SeaLLMs winning "Best Innovate for Impact Award" (news: English Chinese) by The International Telecommunication Union (ITU) of the United Nations, colocated with WAIC.
  • July 2024. We released Version 3 of SeaLLMs (tech memo, demo). V3 supports 10 local languages and achieves SOTA on exam, multiturn, math, and translation among similar-size models. More importantly, it has high reliability, less hallucination, and safer responses in local contexts.
  • June 2024. We released VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs (paper, code).
  • June 2024. We released Auto Arena of LLMs: Automating LLM Evaluations with Agent Peer-battles and Committee Discussions (paper, project page).
  • May 2024. 6 papers were accepted at ACL 2024.
  • April 2024. We released Version 2.5 of SeaLLMs (tech memo, demo).
  • Feb 2024. We released Version 2 of SeaLLMs (tech memo, demo).
  • Jan 2024. Three papers were accepted at ICLR 2024.
  • Nov 2023. We released an LLM, named SeaLLMs (Paper DEMO), which has quite good capabilities for the languages in Southeast Asia.
  • Oct 2023. Seven papers were accepted at EMNLP 2023.
  • Sep 2023. Two papers were accepted at NeurIPS 2023.

Selected Publications (Full List, GitHub, Google Scholar, DBLP)

  • SeaLLMs -- Large Language Models for Southeast Asia [paper] [demo] [code]. Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, Mahani Aljunied, Qingyu Tan, Liying Cheng, Guanzheng Chen, Yue Deng, Sen Yang, Chaoqun Liu, Hang Zhang, Lidong Bing. ACL, 2024.

  • Democratizing LLMs for Low-Resource Languages by Leveraging their English Dominant Abilities with Linguistically-Diverse Prompts [paper]. Xuan-Phi Nguyen, Sharifah Mahani Aljunied, Shafiq Joty, Lidong Bing. ACL, 2024.

  • Exploring the Potential of Large Language Models in Computational Argumentation [paper] [code]. Guizhen Chen, Liying Cheng, Anh Tuan Luu, Lidong Bing. ACL, 2024.

  • PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns [paper] [code]. Yew Ken Chia, Vernon Toh, Deepanway Ghosal, Lidong Bing, Soujanya Poria. ACL, 2024.

  • Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition [paper]. Huiming Wang, Liying Cheng, Wenxuan Zhang, De Wen Soh, Lidong Bing. ACL, 2024.

  • Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning [paper]. Qingyu Tan, Hwee Tou Ng, Lidong Bing. ACL, 2024.

  • Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding [paper] [code]. Sicong Leng, Hang Zhang, Guanzheng Chen, Xin Li, Shijian Lu, Chunyan Miao, Lidong Bing. CVPR, 2024.

  • Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources [paper] [code]. Xingxuan Li, Ruochen Zhao, Yew Ken Chia, Bosheng Ding, Shafiq Joty, Soujanya Poria, Lidong Bing. ICLR, 2024.

  • CLEX: Continuous Length Extrapolation for Large Language Models [paper] [code]. Guanzheng Chen, Xin Li, Zaiqiao Meng, Shangsong Liang, Lidong Bing. ICLR, 2024.

  • Multilingual Jailbreak Challenges in Large Language Models [paper] [code]. Yue Deng, Wenxuan Zhang, Sinno Jialin Pan, Lidong Bing. ICLR, 2024.

  • Sentiment Analysis in the Era of Large Language Models: A Reality Check [paper] [code]. Wenxuan Zhang, Yue Deng, Bing Liu, Sinno Jialin Pan, Lidong Bing. NAACL, 2024.

  • Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning [paper] [code]. Huiming Wang, Liying Cheng, Zhaodonghui Li, De Wen Soh, Lidong Bing. NAACL, 2024.

  • Auto Arena of LLMs: Automating LLM Evaluations with Agent Peer-battles and Committee Discussions [paper] [web site] [leaderboard] [code]. Ruochen Zhao, Wenxuan Zhang, Yew Ken Chia, Deli Zhao, Lidong Bing. Preprint arXiv:2405.20267, 2024.

  • VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs [paper] [code]. Zesen Cheng, Sicong Leng, Hang Zhang, Yifei Xin, Xin Li, Guanzheng Chen, Yongxin Zhu, Wenqi Zhang, Ziyang Luo, Deli Zhao, Lidong Bing. Preprint arXiv:2406.07476, 2024.

  • LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency [paper] [code]. Zhaodonghui Li, Haitao Yuan, Huiming Wang, Gao Cong, Lidong Bing. Preprint arXiv:2404.12872, 2024.

  • How do Large Language Models Handle Multilingualism? [paper] [code]. Yiran Zhao, Wenxuan Zhang, Guizhen Chen, Kenji Kawaguchi, Lidong Bing. Preprint arXiv:2402.18815, 2024.

  • Evaluating Psychological Safety of Large Language Models [paper] [code]. Xingxuan Li, Yutong Li, Lin Qiu, Shafiq Joty, Lidong Bing. Preprint arXiv:2212.10529, 2024.

  • AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging [paper] [code]. Yiran Zhao, Wenxuan Zhang, Huiming Wang, Kenji Kawaguchi, Lidong Bing. Preprint arXiv:2402.18913, 2024.

  • ParaICL: Towards Robust Parallel In-Context Learning [paper] [code]. Xingxuan Li, Xuan-Phi Nguyen, Shafiq Joty, Lidong Bing. Preprint arXiv:2404.00570, 2024.

  • Is translation all you need? a study on solving multilingual tasks with large language models [paper] [code]. Chaoqun Liu, Wenxuan Zhang, Yiran Zhao, Anh Tuan Luu, Lidong Bing. Preprint arXiv:2403.10258, 2024.

  • Contrastive Chain-of-Thought Prompting [paper] [code]. Yew Ken Chia, Guizhen Chen, Luu Anh Tuan, Soujanya Poria, Lidong Bing. Preprint arXiv:2311.09277, 2023.

  • Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs [paper] [code]. Sen Yang, Xin Li, Leyang Cui, Lidong Bing, Wai Lam. Preprint arXiv:2311.09802, 2023.

  • Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding [paper] [code] [demo (Hugging Face)] [demo (ModelScope)] [checkpoints]. Hang Zhang, Xin Li, Lidong Bing. Demo Track of The Conference on Empirical Methods in Natural Language Processing (EMNLP'23 Demo), 2023.

  • Once Upon a Time in Graph: Relative-Time Pretraining for Complex Temporal Reasoning [paper] [code]. Sen Yang, Xin Li, Lidong Bing, Wai Lam. The Conference on Empirical Methods in Natural Language Processing (EMNLP'23), 2023.

  • LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models [paper] [code]. Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Ka-Wei Lee. The Conference on Empirical Methods in Natural Language Processing (EMNLP'23), 2023.

  • Is GPT-4 a Good Data Analyst? [paper] [code]. Liying Cheng, Xingxuan Li, Lidong Bing. Findings of The Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP'23), 2023.

  • Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization [paper] [code]. Chenhui Shen, Liying Cheng, Yang You, Xuan-Phi Nguyen, Lidong Bing. Findings of The Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP'23), 2023.

  • M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models [paper] [code]. Wenxuan Zhang, Sharifah Mahani Aljunied, Chang Gao, Yew Ken Chia, Lidong Bing. Advances in Neural Information Processing Systems 36 (NeurIPS'23), 2023.

  • From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader [paper] [code]. Weiwen Xu, Xin Li, Wenxuan Zhang, Meng Zhou, Wai Lam, Luo Si, Lidong Bing. Advances in Neural Information Processing Systems 36 (NeurIPS'23), 2023.

  • INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models [paper] [code]. Yew Ken Chia, Pengfei Hong, Lidong Bing, Soujanya Poria. Preprint arXiv:2306.04757, 2023.

  • Can ChatGPT-like Generative Models Guarantee Factual Accuracy? On the Mistakes of New Generation Search Engines [paper] [blog article (ZH), (EN)]. Ruochen Zhao, Xingxuan Li, Yew Ken Chia, Bosheng Ding, Lidong Bing. Preprint arXiv:2304.11076, 2023. Follow-up reports by CNN, CNBC, FORTUNE, etc.

  • mPMR: A Multilingual Pre-trained Machine Reader at Scale [paper] [code]. Weiwen Xu, Xin Li, Wai Lam, Lidong Bing. The 61th Annual Meeting of the Association for Computational Linguistics (ACL'23), 2023.

  • Reasoning Implicit Sentiment with Chain-of-Thought Prompting [paper] [code]. Hao Fei, Bobo Li, Qian Liu, Lidong Bing, Fei Li, Tat-Seng Chua. The 61th Annual Meeting of the Association for Computational Linguistics (ACL'23), 2023.

  • Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework [paper] [code]. Ruochen Zhao, Xingxuan Li, Shafiq Joty, Chengwei Qin, Lidong Bing. The 61th Annual Meeting of the Association for Computational Linguistics (ACL'23), 2023.

  • Is GPT-3 a Good Data Annotator? [paper] [code]. Bosheng Ding, Chengwei Qin, Linlin Liu, Yew Ken Chia, Boyang Li, Shafiq Joty, Lidong Bing. The 61th Annual Meeting of the Association for Computational Linguistics (ACL'23), 2023.

  • Improving Self-training for Cross-lingual Named Entity Recognition with Contrastive and Prototype Learning [paper] [code]. Ran Zhou, Xin Li, Lidong Bing, Erik Cambria, Chunyan Miao. The 61th Annual Meeting of the Association for Computational Linguistics (ACL'23), 2023.

  • Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment Analysis [paper] [code]. Yue Deng, Wenxuan Zhang, Sinno Jialin Pan, Lidong Bing. The 61th Annual Meeting of the Association for Computational Linguistics (ACL'23), 2023.

  • Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models [paper] [code]. Qingyu Tan, Hwee Tou Ng, Lidong Bing. The 61th Annual Meeting of the Association for Computational Linguistics (ACL'23), 2023.

Talks

  • Nov 2023. Invited talk on "Research and Implementation of Large Language Models at Alibaba DAMO Academy" at SSNLP 2023.
  • Mar-Apr 2023. Invited talk on "Towards Solving Low-resource & Multilingual NLP Problems and a Pilot Study with LLMs" at Nanjing, Zhejiang, Fudan, and Shanghai Jiao Tong universities.

Professional Service

  • Associate/Action Editor and Reviewer of journals:
    Transactions of the Association for Computational Linguistics (TACL)
    ACM Transactions on Information Systems (TOIS)
    Computational Linguistics (CL)
    IEEE Transactions on Knowledge and Data Engineering (TKDE)
    ACM Transactions on the Web (TWEB)
    ACM Transactions on Intelligent Systems and Technology (ACM TIST)
    Neurocomputing
    Neural Networks
    Neural Computing and Applications (NCA)
    Knowledge-based Systems (KBS)
    Information Processing and Management (IPM)

  • Regular AC, SPC and PC of conferences:
    The Annual Meeting of the Association for Computational Linguistics (ACL)
    The Conference on Empirical Methods in Natural Language Processing (EMNLP)
    The AAAI Conference on Artificial Intelligence (AAAI)
    The International Joint Conference on Artificial Intelligence (IJCAI)
    The Conference on Neural Information Processing Systems (NeurIPS)
    The International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)
    The International World Wide Web Conference (WWW)
    The ACM International Conference on Information and Knowledge Management (CIKM)