Brian Deuksin Kwon

[Soumya Sanyal @ssanyal8]

Interested in evaluating if LMs 🤖 learn logical semantics robustly 💪?

Use our diagnostic dataset RobustLR to test the logical robustness of LMs for deductive reasoning tasks.

https://t.co/C8y9uNMxuw
https://t.co/U5NLXgE3wO

Work w/ @LiaoZeyi @xiangrenNLP

#EMNLP2022

[Han Guo @HanGuo97]

While I'm not at #EMNLP2022, we have two works on the intersection of RL + NLP.

RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
(https://t.co/vfiwSdSFKf)

Efficient (Soft) Q-Learning for Text Generation with Limited Good Data
(https://t.co/D8p1LFhBve)

[Alex Mei @alexmeigz]

Excited to announce I will be presenting my work on "Mitigating Covertly Unsafe Text within Natural Language Systems" at #EMNLP2022 today as part of the NLP for Positive Impact Workshop! Come check it out the poster session at Capital Suite 21A, 3 - 4 PM! https://t.co/nWBWnm9Y17

[Yuxiang Wu @yuxiangwu_]

#EMNLP2022 If you’re interested in incorporating large-scale knowledge into LMs, don't forget to check-out our work “An Efficient Memory-Augmented Transformer for Knowledge-Intensive NLP Tasks”. Work w/ @zhaoyuhitsz, Baotian, @PMinervini, Pontus, @riedelcastro 1/N

[Bill Yuchen Lin @billyuchenlin]

Successfully defended my PhD thesis! 🎓 Extremely grateful to my extraordinary advisor (@xiangrenNLP), mentors (@professorwcohen, @scottyih), awesome collaborators, friends, and family for their continuous support! I can’t imagine life without your guidance & company. ❤️✨