One Temperature to Rule Them All?
cs.LG, cs.AI, cs.CL
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/avivorly/one-temperature
Terminology
Sources
- On the Opportunities and Risks of Foundation Models
- LLaMA: Open and Efficient Foundation Language Models
- GPT-4 Technical Report
- Evaluating Large Language Models Trained on Code
- Program Synthesis with Large Language Models
- Training Verifiers to Solve Math Word Problems
- Scaling Laws for Neural Language Models
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- On the Role of Temperature Sampling in Test-Time Scaling
- Solving math word problems with process- and outcome-based feedback
- Distilling the Knowledge in a Neural Network
- Contextual Temperature for Language Modeling
- $T^2$ of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models
- EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling
- Efficient Prediction of Pass@k Scaling in Large Language Models
- Optimal rounding under integer constraints
- Mistral 7B
- Qwen3 Technical Report
- gpt-oss-120b & gpt-oss-20b Model Card
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis