English(EN) Weighted Ensemble Sampling for Rare-Event Estimation in Language Models

新的加权集成方法改进了LLM中罕见事件的估计

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员开发了加权集成（WE）方法，这是一个新的无训练框架，旨在更有效地估计大型语言模型中罕见但严重的故障的概率。与传统的蒙特卡洛采样或需要辅助提议分布的方法不同，WE直接从语言模型本身进行采样。它利用内部LLM表示作为信号，动态地将其采样预算重新分配给更有可能达到目标罕见事件的前缀。在小型和大型语言模型上进行的与安全相关的任务的实验表明，WE提高了估计这些关键故障概率的效率和可靠性。 AI

影响增强了识别和减轻已部署语言模型中关键故障模式的能力。

排序理由该集群包含一篇详细介绍语言模型新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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: 11 / 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语言模型新方法的论文。[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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Zixuan Liu, Gustavo Didier, Fangzheng Wu, Brian Summa, Zizhan Zheng · 2026-10-15 04:00

语言模型中稀有事件估计的加权集成采样

arXiv:2610.19202v1 Announce Type: new Abstract: Rare but severe failures of large language models can become practically significant at deployment scale. Estimating their probabilities with direct Monte Carlo sampling is highly inefficient, while proposal-based methods typically …

本文如何被排名

报道来源 [1]

语言模型中稀有事件估计的加权集成采样

相关实体

相关话题