English(EN) ANI: Adaptive Numerical Injection for Unifying Semantic and Arithmetic Representations in Numerical Reasoning

新框架ANI将LLM数值推理能力提升9.5个百分点

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

研究人员推出了一种名为自适应数值注入（ANI）的新型框架，旨在提高大型语言模型（LLMs）的数值推理能力。ANI通过根据语义上下文选择性地注入数值特征，解决了文本分词中数字碎片化以及数值嵌入的上下文无关性问题。这种混合方法使用上下文感知门控机制来保留名词标识符，同时增强定量操作数。评估表明，ANI在不影响通用语言基准测试的情况下，使MATH性能比基线模型提高了9.5个百分点。 AI

影响这项研究可能促使LLM在复杂的定量任务中更加可靠，从而可能扩展其在科学和金融领域的应用。

排序理由该集群包含一篇学术论文，详细介绍了一种提高LLM在特定基准测试上性能的新方法。[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: 25 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了一种提高LLM在特定基准测试上性能的新方法。[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: 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) · Jinsung Jeon, Seung-won Hwang · 2026-10-01 04:00

ANI：自适应数值注入，用于统一数值推理中的语义和算术表示

arXiv:2609.39294v1 Announce Type: new Abstract: Precise numerical reasoning with Large Language Models (LLMs) is essential for expanding their applicability to complex real-world tasks. However, text-based tokenization often fragments numbers, significantly hindering precise arit…

本文如何被排名

报道来源 [1]

ANI：自适应数值注入，用于统一数值推理中的语义和算术表示

相关实体

相关话题