Sotabase

Career

· Visiting Researcher, Meta2022–

Publications (16)

Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models
arXiv.org · 2022
183
cited
Bot-Adversarial Dialogue for Safe Conversational Agents
North American Chapter of the Association for Computational Linguistics · 2021
169
cited
In-Context Pretraining: Language Modeling Beyond Document Boundaries
International Conference on Learning Representations · 2023
81
cited
Scaling Expert Language Models with Unsupervised Domain Discovery
arXiv.org · 2023
59
cited
How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds
North American Chapter of the Association for Computational Linguistics · 2020
44
cited
I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents
arXiv.org · 2019
14
cited
Don't Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers
arXiv.org · 2021
6
cited
FlexOlmo: Open Language Models for Flexible Data Use
arXiv.org · 2025
5
cited
Overconfidence in the Face of Ambiguity with Adversarial Data
DADC · 2022
2
cited
Precise Information Control in Long-Form Text Generation
arXiv.org · 2025
2
cited
BotsTalk: Machine-Sourced Framework for Automatic Curation of Large-scale Multi-skill Dialogue Datasets
2021
S AFETY B ENCH : Identifying Safety-Sensitive Situations for Open-domain Conversational Systems
2021
Self-chats from Large Language Models Make Small ChatPal Better Anonymous ACL submission
Sotabase
Margaret Li | Researcher Profile | Sotabase | Sotabase