Hi, I am Shibo Hao, a Ph.D. student at UC San Diego, Halıcıoğlu Data Science Institute (HDSI). My advisor is Professor Zhiting Hu. Previously, I obtained my B.S. degree in Computer Science from Peking University.
My research interest lies in large language models (LLMs). Specifically, I aim to design principled methods to enhance the reasoning ability of LLMs (Reasoning-via-planning, LLM Reasoners), augment LLMs with external tools (ToolkenGPT), and interpret the knowledge of language models (BertNet). My goal is to create general autonomous agents based on foundation models, which will possess the ability to perceive, take actions, and learn from their embodied environments.
|Nov 17, 2023||Our paper ToolkenGPT received the best paper award at SoCalNLP 2023🎉!|
|Nov 17, 2023||I will attend SoCal NLP Symposium 2023 and present our two recent papers.|
|Nov 7, 2023||Invited talk at Mila - Quebec AI Institute and ServiceNow Research.|
|Oct 25, 2023||Reasoning via Planning (RAP) has been featured in State of AI Report 2023.|
|Oct 8, 2023||Reasoning via Planning (RAP) is accepted to EMNLP 2023!|
|Oct 1, 2023||Invited to serve as a Reviewer for ACL Rolling Review (ARR) - Octember.|
|Sep 22, 2023||Excited to share that ToolkenGPT is accepted to NeurIPS 2023 as an oral presentation!|
|Jul 29, 2023||Introducing LLM Reasoners, a library for advanced reasoning with LLMs.|
- ACLIn Findings of the Association for Computational Linguistics: ACL 2023, 2023
- NeurIPSAdvances in Neural Information Processing Systems (oral), 2023Best Paper Award at SoCalNLP 2023
- EMNLPIn Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023