Jacob Eisenstein

Google (United States) — United States

Computer Science · Physical Sciences

47h-index10.5kcitations226works0.32yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(98), Natural Language Processing Techniques(85), Speech and dialogue systems(31), Digital Communication and Language(22), Complex Network Analysis Techniques(19)

Publications226 total

Learning Steerable Clarification Policies with Collaborative Self-play
arXiv (Cornell University)·2025Open Access
Plantain: Plan-Answer Interleaved Reasoning
arXiv (Cornell University)·2025Open Access
Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
arXiv (Cornell University)·2025Open Access
Cost-Optimal Active AI Model Evaluation
arXiv (Cornell University)·2025Open Access
Social Media as a Sociolinguistic Resource
2025
Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models
2025Open Access
InfAlign: Inference-aware language model alignment
arXiv (Cornell University)·2024Open Access
ALTA: Compiler-Based Analysis of Transformers
arXiv (Cornell University)·2024· 1 citedOpen Access
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning
arXiv (Cornell University)·2024· 2 citedOpen Access
Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models
arXiv (Cornell University)·2024Open Access
Robust Preference Optimization through Reward Model Distillation
arXiv (Cornell University)·2024· 1 citedOpen Access
Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment
arXiv (Cornell University)·2024Open Access
Transforming and Combining Rewards for Aligning Large Language Models
arXiv (Cornell University)·2024Open Access
Theoretical guarantees on the best-of-n alignment policy
arXiv (Cornell University)·2024· 1 citedOpen Access
Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment
2024Open Access
Reward Model Ensembles
TIB Data Manager·2024Open Access
Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking
arXiv (Cornell University)·2023· 2 citedOpen Access
MD3: The Multi-Dialect Dataset of Dialogues
2023· 2 cited
Selectively Answering Ambiguous Questions
arXiv (Cornell University)·2023Open Access
MD3: The Multi-Dialect Dataset of Dialogues
arXiv (Cornell University)·2023Open Access
page 1 of 12Next →

Frequent Co-authors

Yangfeng Ji(7), Eric P. Xing(6), Ángel Puerta(6), Umashanthi Pavalanathan(5), Brendan O’Connor(4), Regina Barzilay(4), Kevin Gimpel(3), Nathan Schneider(3), Dipanjan Das(3), Michael Heilman(3), Dani Yogatama(3), Noah A. Smith(3), Noah A. Smith(3), Éric Gilbert(3), Amr Ahmed(3), Jeffrey Flanigan(2), Victor Veitch(2), Eshwar Chandrasekharan(2), Yi Luan(2), Kristina Toutanova(2)