English(EN) AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs

AdaFuse框架通过自适应集成提升大型语言模型性能

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

研究人员推出AdaFuse，一个旨在通过解码过程中的自适应集成来提升大型语言模型（LLMs）性能的新框架。与使用固定融合策略的现有方法不同，AdaFuse根据解码上下文动态选择合适的融合单元，实现中途生成适应。该框架采用基于不确定性的标准来决定何时进行集成，并调用一种感知多样性的缩放策略来探索替代性续写并提高集成质量。实验表明，AdaFuse在问答、算术推理和机器翻译等各种任务上始终优于强大的集成基线，平均相对提升了6.88%。 AI

影响这种自适应集成技术有望在各种应用中实现更高效、更准确的大型语言模型输出。

排序理由该集群包含一篇详细介绍大型语言模型集成新方法的论文。[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: 24 / 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大型语言模型集成新方法的论文。[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) · Chengming Cui, Tianxin Wei, Ziyi Chen, Ruizhong Qiu, Zhichen Zeng, Zhining Liu, Xuying Ning, Duo Zhou, Jingrui He · 2026-09-01 04:00

AdaFuse：用于大型语言模型的测试时自适应集成解码

arXiv:2601.06022v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling provides a practical way to combine these ca…

本文如何被排名

报道来源 [1]

AdaFuse：用于大型语言模型的测试时自适应集成解码

相关实体

相关话题