English(EN) Diverse by Reasoning: Harnessing the Wisdom of LLM Crowds for Future Prediction

通过行为聚类改进的大型语言模型（LLM）群体用于未来预测

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-26 04:00

研究人员开发了一个新颖的框架，以提高大型语言模型（LLM）进行的未来预测的准确性。该方法侧重于通过根据模型在开发任务中的推理轨迹进行聚类来创建多样化的大型语言模型（LLM）群体。这种方法选择代表性模型，与使用更大但多样性较低的群体相比，性能更好。使用 K-means++ 聚类选择的三模型群体在预测基准测试中的表现优于 25 模型群体，同时显著降低了计算成本。 AI

影响这项研究通过优化大型语言模型（LLM）群体构成，有望实现更准确、更具成本效益的由人工智能驱动的未来预测。

排序理由这是一篇详细介绍改进大型语言模型（LLM）性能新方法的论文。[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: 43 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍改进大型语言模型（LLM）性能新方法的论文。[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, model release; 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) · Nirupam Chetlapalli, Yiming Liao, Min-Chun Chen, Keke Chen · 2026-08-26 04:00

以推理实现多样化：利用大型语言模型群体的智慧进行未来预测

arXiv:2608.24001v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for future prediction, motivating the use of multiple models as a wisdom-of-the-crowd mechanism. However, simply increasing crowd size does not guarantee effective diversity, as dif…

本文如何被排名

报道来源 [1]

以推理实现多样化：利用大型语言模型群体的智慧进行未来预测

相关实体

相关话题