Sotabase

Career

· Research Scientist, MIT

Publications (183)

The spread of true and false news online
Science · 2018
6,757
cited
A Survey of Data Augmentation Approaches for NLP
Findings · 2021
927
cited
Language Models are Multilingual Chain-of-Thought Reasoners
International Conference on Learning Representations · 2022
519
cited
Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval · 2016
179
cited
Me, My Echo Chamber, and I: Introspection on Social Media Polarization
The Web Conference · 2018
156
cited
Rumor Gauge
ACM Transactions on Knowledge Discovery from Data · 2017
128
cited
Training Socially Aligned Language Models in Simulated Human Society
arXiv.org · 2023
128
cited
Data Boost: Text Data Augmentation through Reinforcement Learning Guided Conditional Generation
Conference on Empirical Methods in Natural Language Processing · 2020
113
cited
Automatic detection and verification of rumors on Twitter
2015
112
cited
Mitigating Political Bias in Language Models Through Reinforced Calibration
AAAI Conference on Artificial Intelligence · 2021
109
cited
Mind's Eye: Grounded Language Model Reasoning through Simulation
International Conference on Learning Representations · 2022
96
cited
Training Socially Aligned Language Models on Simulated Social Interactions
International Conference on Learning Representations · 2023
90
cited
DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs
International Workshop on Semantic Evaluation · 2016
77
cited
Judging the Judges: A Systematic Investigation of Position Bias in Pairwise Comparative Assessments by LLMs
arXiv.org · 2024
76
cited
Tweet Acts: A Speech Act Classifier for Twitter
International Conference on Web and Social Media · 2016
71
cited
Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
North American Chapter of the Association for Computational Linguistics · 2021
66
cited
Aligning Generative Language Models with Human Values
NAACL-HLT · 2022
65
cited
Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
2024
60
cited
Enhanced Twitter Sentiment Classification Using Contextual Information
WASSA@EMNLP · 2015
48
cited
Twitter Demographic Classification Using Deep Multi-modal Multi-task Learning
Annual Meeting of the Association for Computational Linguistics · 2017
46
cited
Sotabase