FIELD NOTES TOPIC
confidence estimation
2 notes, newest first.
From Critic to Confidence: PPO for Language-Based Quantitative Prediction with Confidence Estimation
Researchers introduce a new framework called CARE-PPO to improve language-based quantitative prediction by both accurately estimating numerical values and providing reliable confidence signals. The method uses…
Future Confidence Distillation in Large Language Models
The paper investigates how the confidence of large language models evolves during the answering process. It compares pre-solution and post-solution confidence estimates across different models and finds that…
