Sotabase
Home
Researchers
Career
·
Software Engineer
,
OpenAI
2026–
·
Software Engineer
,
Meta
2019–2025
·
Research Assistant
,
UC Berkeley RISELab
2017–2019
·
BS in EECS
,
University of California, Berkeley
2015–2019
Publications
(24)
The Llama 3 Herd of Models
2024
12,282
cited
SHADES: Towards a Multilingual Assessment of Stereotypes in Large Language Models
North American Chapter of the Association for Computational Linguistics · 2025
12
cited
PyTorch RPC: Distributed Deep Learning Built on Tensor-Optimized Remote Procedure Calls
Conference on Machine Learning and Systems · 2023
6
cited
When Every Token Counts: Optimal Segmentation for Low-Resource Language Models
COLING Workshops · 2024
6
cited
OPI-DRO-HEL at SemEval-2025 Task 11: Few-shot prompting for Text-based Emotion Recognition
2
cited
A benchmark system for evaluating Hungarian generative LLMs
1
cited
Can dependency parses facilitate generalization in language models? A case study of cross-lingual relation extraction
Proceedings of the 4th International Workshop on Knowledge-Augmented Methods for Natural Language Processing · 2025
1
cited
Dialect Normalization using Large Language Models and Morphological Rules
Annual Meeting of the Association for Computational Linguistics · 2025
1
cited
“I Need More Context and an English Translation”: Analysing How LLMs identify Personal Information in Komi, Polish, and English
1
cited
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
2026
1
cited
A 3 : Automatic Alignment Framework for Attributed Text Generation
DeepFake Image Detection
2020
Evaluating Design Choices in Verifiable Generation with Open-source Models
Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025) · 2025
Fast LLM Inference with Parallel Prompting
From Prototypical to Relational: How LLMs Navigate Complex Analogies
Jailbreak Distillation: Renewable Safety Benchmarking
Conference on Empirical Methods in Natural Language Processing · 2025
Learning What to Remember: Adaptive Probabilistic Memory Retention for Memory-Efficient Language Models A Probabilistic Framework for Memory-Constrained Language Modeling
Logically Constrained Decoding
Proceedings of The 3rd Workshop on Mathematical Natural Language Processing (MathNLP 2025) · 2025
PyTorch distributed
2020
Router-Tuning: A Simple and Effective Approach for Dynamic Depth
Conference on Empirical Methods in Natural Language Processing · 2025
Show all 24 papers →
Sotabase
Omkar Salpekar | Researcher Profile | Sotabase | Sotabase