Donghee Choi
@donghee.bsky.social
Assistant Professor at Pusan National University (https://sites.google.com/view/pnu-clink)
Former Research Associate at Imperial College London.
Bio/Clinical NLP, Food/Financial AI
Former Research Associate at Imperial College London.
Bio/Clinical NLP, Food/Financial AI
Excited to share that my paper has been accepted as an Applied Research paper at #CIKM2025! 🎉 www.linkedin.com/posts/jinkyu...
#cikm2025 #quantfinance #portfoliooptimization #reinforcementlearning #deeplearning #trading #aiinfinance | Jinkyu Kim
🚀 Thrilled to share that our paper, “DeepAries: Adaptive Rebalancing Interval Selection for Enhanced Portfolio Selection,” has been accepted to CIKM 2025!
We focused on a critical, yet often overlooke...
www.linkedin.com
November 4, 2025 at 8:22 AM
Excited to share that my paper has been accepted as an Applied Research paper at #CIKM2025! 🎉 www.linkedin.com/posts/jinkyu...
Reposted by Donghee Choi
Excited to share our ICLR and NAACL papers! Please come and say hi, we're super friendly :)
April 22, 2025 at 6:42 PM
Excited to share our ICLR and NAACL papers! Please come and say hi, we're super friendly :)
Reposted by Donghee Choi
Do LLMs need rationales for learning from mistakes? 🤔
When LLMs learn from previous incorrect answers, they typically observe corrective feedback in the form of rationales explaining each mistake. In our new preprint, we find these rationales do not help, in fact they hurt performance!
🧵
When LLMs learn from previous incorrect answers, they typically observe corrective feedback in the form of rationales explaining each mistake. In our new preprint, we find these rationales do not help, in fact they hurt performance!
🧵
February 13, 2025 at 3:38 PM
Do LLMs need rationales for learning from mistakes? 🤔
When LLMs learn from previous incorrect answers, they typically observe corrective feedback in the form of rationales explaining each mistake. In our new preprint, we find these rationales do not help, in fact they hurt performance!
🧵
When LLMs learn from previous incorrect answers, they typically observe corrective feedback in the form of rationales explaining each mistake. In our new preprint, we find these rationales do not help, in fact they hurt performance!
🧵