Bryan Hooi
@BryanHooi1
Assistant Prof at NUS
ID:1500921140512174081
http://bhooi.github.io 07-03-2022 19:47:50
7 Tweets
102 Followers
82 Following
Delighted to announce that our work has been accepted for presentation at the ICLR 2024 LLM Agents Workshop@ICLR2024 workshop in Vienna. Received exceptionally positive feedback from the reviewers and looking forward to sharing our insights and contributions with the community.
Thrilled to share paper on LLMs' calibration capability! 'Can LLMs Express Their Uncertainty?'
We explore confidence elicitation in LLM,revealing mitigation of LLMs' overconfidence. However,improvements are needed.
Arxiv: arxiv.org/abs/2306.13063
#LLM #Calibration #Uncertainty
New paper w/ Xiaoxin He, T. Laurent, Bryan Hooi 'Explanations as Features: LLM-Based Features for Text-Attributed Graphs'
ArXiv: arxiv.org/pdf/2305.19523โฆ
GitHub: github.com/XiaoxinHe/TAPE