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.
insights
Post-training NVIDIA Nemotron 3.5 Lightning for enterprise domains
Published: August 11, 2026
Using post-training techniques to improve model performance.
insights
EAGLE-3 speculative decoding for NVIDIA Nemotron 3.5 Lightning
Published: August 11, 2026
Experimenting with speculative decoding using the EAGLE-3 draft head.
Publications and resources
Browse the full set of Thoughtworks AI Research Labs materials, including research papers, technical explainers, open-source code and datasets.
Teaching a model to stop writing like a model
EAGLE-3 speculative decoding for NVIDIA Nemotron 3.5 Lightning
Experimenting with speculative decoding using the EAGLE-3 draft head.
Post-training NVIDIA Nemotron 3.5 Lightning for enterprise domains
Using post-training techniques to improve model performance.
Cultural counterfactuals
Curveball steering — Geometry-aware non-linear steering to control LLM behavior
Anti-slopping — An innovation for rectifying LLM writing clichés
Concept consistency score
p-less sampling: A robust LLM decoding strategy
Steering smarter
Evaluating LLM-generated summaries using the Lie algebra framework
Beyond I am sorry, I can’t: dissecting large language model refusal
Distribution-aware feature selection for SAEs
Towards transparent AI grading: Entropy as a signal for human-AI disagreement
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.
Beyond linear steering: Unified multi-attribute control for language models
Calculating uncertainty in generative AI
Dropout estimates model uncertainty cost-effectively using prediction variance or softmax entropy while improving generalization and reducing overfitting.
TinySQL
Evaluating LLMs using semantic entropy
LLM benchmarks, evals and tests
Evaluating LLM apps is hard due to open-ended outputs, variable behavior, complex reasoning and diverse real-world tasks.
Turning up the heat: Min-p samling for creative and coherent creative outputs
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.
Teaching a model to stop writing like a model
EAGLE-3 speculative decoding for NVIDIA Nemotron 3.5 Lightning
Experimenting with speculative decoding using the EAGLE-3 draft head.
Post-training NVIDIA Nemotron 3.5 Lightning for enterprise domains
Using post-training techniques to improve model performance.
Cultural counterfactuals
Curveball steering — Geometry-aware non-linear steering to control LLM behavior
Anti-slopping — An innovation for rectifying LLM writing clichés
Concept consistency score
p-less sampling: A robust LLM decoding strategy
Steering smarter
Evaluating LLM-generated summaries using the Lie algebra framework
Beyond I am sorry, I can’t: dissecting large language model refusal
Distribution-aware feature selection for SAEs
Towards transparent AI grading: Entropy as a signal for human-AI disagreement
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.
Beyond linear steering: Unified multi-attribute control for language models
Calculating uncertainty in generative AI
Dropout estimates model uncertainty cost-effectively using prediction variance or softmax entropy while improving generalization and reducing overfitting.
TinySQL
Evaluating LLMs using semantic entropy
LLM benchmarks, evals and tests
Evaluating LLM apps is hard due to open-ended outputs, variable behavior, complex reasoning and diverse real-world tasks.
Turning up the heat: Min-p samling for creative and coherent creative outputs
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.
Antislop: A Comprehensive Framework for Identifying and Eliminating Repetitive Patterns in Language Models
p-less Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding
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