English(EN) BiG-SURE - Bipartite Graph for Semantic Uncertainty and Reliability Estimation of LLMs

新的BiG-SURE方法在黑盒设置下估计LLM的不确定性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-01 04:00

研究人员开发了BiG-SURE，一种用于估计大型语言模型（LLM）和视觉语言模型（VLM）不确定性和可靠性的新颖方法，特别是在模型参数无法访问的黑盒场景中。该技术使用来自低温度（稳定）和高温度（探测）模型响应的基于NLI的蕴含分数来构建二分图。然后，置信度从该图的光谱能量中导出，不确定性由其补数衡量。BiG-SURE在各种QA任务中展示了改进的弃权准确性，提供了一种简单、无监督的模型可靠性评估方法。 AI

影响通过提供一种强大的黑盒不确定性估计方法，增强了LLM和VLM在关键应用中的安全性和可靠性。

排序理由该集群包含一篇详细介绍LLM不确定性估计新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 30 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍LLM不确定性估计新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Debarpan Bhattacharya, Malay Phadke, Sriram Ganapathy · 2026-09-01 04:00

BiG-SURE - 用于大语言模型语义不确定性和可靠性估计的二分图

arXiv:2608.30646v1 Announce Type: cross Abstract: Reliable uncertainty estimation is a crucial requirement for deploying large language models (LLMs) and vision-language models (VLMs) in safety-critical settings, especially when the model parameters are not accessible (black-box)…

本文如何被排名

报道来源 [1]

BiG-SURE - 用于大语言模型语义不确定性和可靠性估计的二分图

相关实体

相关话题