Unsupervised single-generation confidence calibration for reasoning LLMs via offline self-consistency proxy distillation outperforms baselines on math and QA tasks and improves selective prediction.
Your pre-trained LLM is secretly an unsupervised confidence calibrator
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Training LLMs to verbalize uncertainty explicitly at the end or during reasoning reduces overconfident errors and improves answer quality on factual tasks while enabling RAG triggers.
A deep research agent incorporates progressive confidence estimation and calibration to produce trustworthy reports with transparent confidence scores on claims.
citing papers explorer
-
Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation
Unsupervised single-generation confidence calibration for reasoning LLMs via offline self-consistency proxy distillation outperforms baselines on math and QA tasks and improves selective prediction.
-
LLMs Should Express Uncertainty Explicitly
Training LLMs to verbalize uncertainty explicitly at the end or during reasoning reduces overconfident errors and improves answer quality on factual tasks while enabling RAG triggers.
-
Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration
A deep research agent incorporates progressive confidence estimation and calibration to produce trustworthy reports with transparent confidence scores on claims.
- MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination