Sledovať
Weiyan Shi
Weiyan Shi
Northeastern University
Overená e-mailová adresa na: northeastern.edu - Domovská stránka
Názov
Citované v
Citované v
Rok
Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good
X Wang*, W Shi*, R Kim, Y Oh, S Yang, J Zhang, Z Yu
🏆 ACL 2019 Best Paper Nomination, 2019
3132019
Human-level play in the game of Diplomacy by combining language models with strategic reasoning
Meta Fundamental AI Research Diplomacy Team (FAIR)†, A Bakhtin, ...
Science 378 (6624), 1067-1074, 2022
2632022
How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms
Y Zeng, H Lin, J Zhang, D Yang, R Jia, W Shi
🏆 ACL 2024 Best Social Impact Paper, 2024
2112024
Inspired: Toward sociable recommendation dialog systems
SA Hayati, D Kang, Q Zhu, W Shi, Z Yu
EMNLP 2020, 2020
1472020
Effects of persuasive dialogues: testing bot identities and inquiry strategies
W Shi, X Wang, YJ Oh, J Zhang, S Sahay, Z Yu
Proceedings of the 2020 CHI conference on human factors in computing systems …, 2020
1062020
Sentiment adaptive end-to-end dialog systems
W Shi, Z Yu
ACL 2018, 2018
952018
How to Build User Simulators to Train RL-based Dialog Systems
W Shi, K Qian, X Wang, Z Yu
EMNLP 2019, 2019
752019
Selective differential privacy for language modeling
W Shi, A Cui, E Li, R Jia, Z Yu
NAACL 2021, 2021
672021
Just fine-tune twice: Selective differential privacy for large language models
W Shi, R Shea, S Chen, C Zhang, R Jia, Z Yu
arXiv preprint arXiv:2204.07667, 2022
552022
Unsupervised Dialog Structure Learning
W Shi, T Zhao, Z Yu
NAACL 2019, 2019
502019
End-to-end trainable non-collaborative dialog system
Y Li, K Qian, W Shi, Z Yu
Proceedings of the AAAI Conference on Artificial Intelligence 34 (05), 8293-8302, 2020
452020
The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
R Xu, BS Lin, S Yang, T Zhang, W Shi, T Zhang, Z Fang, W Xu, H Qiu
🏆 ACL 2024 Outstanding Paper, 2023
442023
Structured attention for unsupervised dialogue structure induction
L Qiu, Y Zhao, W Shi, Y Liang, F Shi, T Yuan, Z Yu, SC Zhu
arXiv preprint arXiv:2009.08552, 2020
392020
A safe harbor for ai evaluation and red teaming
S Longpre, S Kapoor, K Klyman, A Ramaswami, R Bommasani, ...
arXiv preprint arXiv:2403.04893, 2024
342024
Refine and imitate: Reducing repetition and inconsistency in persuasion dialogues via reinforcement learning and human demonstration
W Shi, Y Li, S Sahay, Z Yu
arXiv preprint arXiv:2012.15375, 2020
302020
Controllable mixed-initiative dialogue generation through prompting
M Chen, X Yu, W Shi, U Awasthi, Z Yu
arXiv preprint arXiv:2305.04147, 2023
242023
Culturebank: An online community-driven knowledge base towards culturally aware language technologies
W Shi, R Li, Y Zhang, C Ziems, R Horesh, RA de Paula, D Yang
arXiv preprint arXiv:2404.15238, 2024
192024
Social influence dialogue systems: A survey of datasets and models for social influence tasks
K Chawla, W Shi, J Zhang, G Lucas, Z Yu, J Gratch
arXiv preprint arXiv:2210.05664, 2022
192022
Towards socially intelligent agents with mental state transition and human value
L Qiu, Y Zhao, Y Liang, P Lu, W Shi, Z Yu, SC Zhu
Proceedings of the 23rd Annual Meeting of the Special Interest Group on …, 2022
182022
When life gives you lemons, make cherryade: Converting feedback from bad responses into good labels
W Shi, E Dinan, K Shuster, J Weston, J Xu
arXiv preprint arXiv:2210.15893, 2022
172022
Systém momentálne nemôže vykonať operáciu. Skúste to neskôr.
Články 1–20