Toloka Research
Our mission
Our team strives to enhance the capabilities and safety of frontier models with valuable data, advanced training and evaluation methods
New data collection methods
for SFT and RLHF that leverage synthetic data, AI feedback, and expert human-generated data.
Improved approaches to model training and alignment
that enhance model capabilities in long-horizon reasoning and autonomous behavior.
High-quality evaluation metrics & benchmarks to measure performance in coding, math, reasoning, multilingualism, multimodality, and other complex tasks.
Red-teaming methods for identifying model vulnerabilities and developing safety metrics such as harmfulness, security and CBRN risks, social bias, and more.
Our projects
Publications
arXiv 2023
arXiv 2023
arXiv 2023
Conferences and events
We regularly hold tutorials and lead workshops at some of the biggest AI conferences around the globe.
