Shibo Hao
Ph.D. student at UCSD
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.
I aim to design principled methods to enhance the reasoning ability of foundation models (especially LLMs). This includes building a system-2 reasoning framework with a world model (Pandora) and a search algorithm for planning (Reasoning via planning). Besides, I’m also interested in new training methods (Flow of Reasoning) and augmenting LLMs with external tools (ToolkenGPT). We are maintaining a library (LLM Reasoners) for reasoning algorithms in a unified formulation.
News
| Jul 10, 2024 | LLM Reasoners is accepted to the first Conference of Language Modeling (COLM 2024). |
|---|---|
| May 24, 2024 | Check out 𝒫𝒶𝓃𝒹𝑜𝓇𝒶, our new work towards a general world model 🌎 |
| Apr 8, 2024 | LLM Reasoners is accepted to ICLR 2024 LLM Agent workshop. |
| Nov 17, 2023 | Our paper ToolkenGPT received the best paper award at SoCalNLP 2023🎉! |
| 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! |
| Sep 22, 2023 | Excited to share that ToolkenGPT is accepted to NeurIPS 2023 as an oral presentation! |
Selected publications
2024
- COLMIn Conference on Language Model (COLM), 2024Also to appear at Large Language Model (LLM) Agents workshop at ICLR 2024
2023
- NeurIPS
- EMNLPIn Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023
- ACLIn Findings of the Association for Computational Linguistics: ACL 2023, 2023