English(EN) Multi-Token Prediction and Alternative Tokenization Improve Learning Latent Multi-Hop Graph Search at Scale

新方法使语言模型能够大规模学习复杂的图搜索任务

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

研究人员确定了阻碍语言模型大规模学习潜在多跳图搜索能力的两个关键因素：监督信号和令牌化方法。通过实施多令牌预测 (MTP) 和替代令牌化，他们克服了先前的扩展限制。这些进步使模型能够比以前可能实现的规模大得多地一致且稳定地解决该任务。 AI

影响使语言模型在基于图的任务中能够进行更复杂的推理和问题解决。

排序理由研究论文，详细介绍了改进语言模型在特定任务上性能的新颖方法。[lever_c_demoted from research: ic=1 ai=1.0]

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: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了改进语言模型在特定任务上性能的新颖方法。[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: 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。

arXiv cs.CL TIER_1 English(EN) · Arvid Frydenlund, FuTe Wong, Katherine Lambert, Frank Rudzicz · 2026-10-23 04:00

Multi-Token Prediction and Alternative Tokenization Improve Learning Latent Multi-Hop Graph Search at Scale

arXiv:2610.31439v1 Announce Type: cross Abstract: Given an unseen graph, a start node, $s$, and an end node, $t$, can a language model generate the shortest path from $s$ to $t$? Prior work has found that models fail to learn this task as the graphs scale. We show that this failu…