|
I am a PhD student at Wuhan University, supervised by Prof. Donghong Ji (姬东鸿). My research explores LLM interpretability, AI alignment, and adaptive agents. My general research interests lie in natural language processing, machine learning and cognitive science. I value theoretical work that pushes the boundaries of human knowledge and engineering solutions that address practical problems. Email: limengnlp@whu.edu.cn / Twitter / Google Scholar / Github |
|
|
|
 |
Paper / Code ACL 2025 (Oral) The expressions of uncertainty generated by LLMs are not always reliable, and it is necessary to enrich semantic knowledge of epistemic modality in LLMs. |
 |
Paper / Code & Appendix CogSci 2024 RNN and Transformer models illustrate a certain ability in learning part-whole hierarchies, but they do not have robust compositional reasoning. |
|
|
|
|
|
|
