Human-Centric-Machine-Learning/tokenization-multiplicity-data
Updated
•
16
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
Human-Centric Machine Learning
Max Planck Institute for Software Systems
📚 Featured Research
Test-Time Compute Games Strategic behavior in LLM-as-a-service markets.
- 📄 Read the Paper
- 💻 View Code (GitHub)
- 💾 Download Dataset — Contains full inference traces: sampled answers, token counts, correctness labels, and Best-of-N scores.
Tokenization Multiplicity Leads to Arbitrary Price Variation in LLM-as-a-service Solving tokenization multiplicity with a simple and efficient sampling method.
models
0
None public yet