1
Counterfactual Graph for Multi-Agent LLM Calibration
用反事实图校准多智能体大模型的不确定性，提升群体决策可靠性。
arXiv:2605.30653v1 Announce Type: new Abstract: Multi-agent LLM systems often treat agreement as evidence: when many agents in a panel give the same a…
2
Human-Alignment and Calibration of Inference-Time Uncertainty in Large Language Models
让大语言模型的不确定性估计更贴近人类判断，这篇论文提出了一种推理时校准方法，提升模型可信度。
arXiv:2508.08204v2 Announce Type: replace-cross Abstract: There has been much recent interest in evaluating large language models for uncertainty cali…
3
Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting
新方法让大模型预测时的置信度更贴近人类的不确定性，提升对齐效果。
arXiv:2605.27668v1 Announce Type: cross Abstract: Probabilistic forecasting estimates the likelihood of uncertain future events. To improve LLM foreca…