Sotabase

Career

· Senior Research Scientist, Google DeepMind2024–

Publications (52)

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
arXiv.org · 2025
1,636
cited
Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
NAACL-HLT · 2023
370
cited
Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
Annual Meeting of the Association for Computational Linguistics · 2022
337
cited
Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias
Neural Information Processing Systems · 2023
323
cited
Weakly-Supervised Neural Text Classification
International Conference on Information and Knowledge Management · 2018
190
cited
Weakly-Supervised Hierarchical Text Classification
AAAI Conference on Artificial Intelligence · 2018
137
cited
TaxoGen: Unsupervised Topic Taxonomy Construction by Adaptive Term Embedding and Clustering
Knowledge Discovery and Data Mining · 2018
117
cited
SetExpan: Corpus-Based Set Expansion via Context Feature Selection and Rank Ensemble
ECML/PKDD · 2017
91
cited
LiPO: Listwise Preference Optimization through Learning-to-Rank
North American Chapter of the Association for Computational Linguistics · 2024
86
cited
Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion
Findings · 2021
84
cited
HiExpan: Task-Guided Taxonomy Construction by Hierarchical Tree Expansion
Knowledge Discovery and Data Mining · 2018
84
cited
TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class Names
North American Chapter of the Association for Computational Linguistics · 2021
76
cited
Building Math Agents with Multi-Turn Iterative Preference Learning
International Conference on Learning Representations · 2024
61
cited
End-to-End Reinforcement Learning for Automatic Taxonomy Induction
Annual Meeting of the Association for Computational Linguistics · 2018
54
cited
Empower Entity Set Expansion via Language Model Probing
Annual Meeting of the Association for Computational Linguistics · 2020
48
cited
RRM: Robust Reward Model Training Mitigates Reward Hacking
International Conference on Learning Representations · 2024
48
cited
Taxonomy Completion via Triplet Matching Network
AAAI Conference on Artificial Intelligence · 2021
44
cited
AceMap: A Novel Approach towards Displaying Relationship among Academic Literatures
The Web Conference · 2016
31
cited
Mining Entity Synonyms with Efficient Neural Set Generation
AAAI Conference on Artificial Intelligence · 2018
29
cited
Entity Set Search of Scientific Literature: An Unsupervised Ranking Approach
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval · 2018
28
cited
Sotabase