Our research
We focus on rigorous evaluation, interpretability, robustness and model control: how AI behaves, where it fails and how it can be guided. We also explore model interoperability and AI decision-making.
Read the research. Use the code.
Browse the Labs’ projects to access the research behind each one, with links to papers, code and datasets where available. Access the methods, run the code and build on the results.
p-less sampling: A robust LLM decoding strategy
In this research paper, we introduce a novel approach of sampling named 𝜌-less sampling for text generation in autoregressive models.
The next frontiers in AI — according to industry leaders
Published: June 04, 2025
AI is evolving fast. Keynotes and events reveal the most important emerging trends and narratives shaping generative AI today.
More research
The next frontiers in AI — according to industry leaders
AI is evolving fast. Keynotes and events reveal the most important emerging trends and narratives shaping generative AI today.
Calculating uncertainty in generative AI
Dropout estimates model uncertainty cost-effectively using prediction variance or softmax entropy while improving generalization and reducing overfitting.
LLM benchmarks, evals and tests
Evaluating LLM apps is hard due to open-ended outputs, variable behavior, complex reasoning and diverse real-world tasks.
Decoding LLM uncertainties for better predictability
We present two model uncertainty measures: structural uncertainty (using token entropy) and conceptual uncertainty (via embedding cosine distances).
A surprisingly effective way to estimate token importance in LLM prompts
We explore a proof-of-concept tool to gauge individual token importance within prompts using text embeddings, excited to build on it with the community.
Probabilistic machine learning and weak supervision
We demonstrate a proof of principle for human-machine collaboration to label training data and build ML models using probabilistic rather than hard labels.
A gentle introduction to machine teaching
While ML focuses on optimizing algorithms, Machine Teaching addresses AI's domain expertise bottleneck by making humans more effective at teaching models.
Partners and collaborations
Thoughtworks AI labs sit within a wider network of organizations spanning public AI research, semiconductor innovation, cloud platforms, open source and AI engineering.
These relationships strengthen the lab’s ability to contribute to the methods, tools and technical standards shaping reliable AI.
For partnerships and collaboration inquiries
email ai-labs@thoughtworks.com