TECP: Token-Entropy Conformal Prediction for LLMs
Uncertainty quantification (UQ) for open-ended language generation remains a critical yet underexplored challenge, particularly in settings where token-level log-probabilities are available during decoding. We present <b>Token-Entropy Conformal Prediction (TECP)</b>, which treats a log-probability-b...
保存先:
| 主要な著者: | , |
|---|---|
| フォーマット: | Artigo |
| 言語: | Inglês |
| 出版事項: |
MDPI AG
2025-10-01
|
| シリーズ: | Mathematics |
| 主題: | |
| オンライン･アクセス: | https://www.mdpi.com/2227-7390/13/20/3351 |
| タグ: |
タグなし, このレコードへの初めてのタグを付けませんか!
|