PulseAugur
中
实时 20:32:06
English(EN) REAP: Relation-Aware Elicitation and Parsing for Closed-Book Knowledge Base Construction from LLMs

REAP系统从大型语言模型中提取知识,用于AKBC共享任务2026

研究人员开发了一个名为REAP的系统,用于AKBC共享任务2026,该任务专注于从语言模型中构建知识库,而无需进行微调。REAP利用结构化的思维链推理和特定关系查询来提取知识,然后将其格式化为JSON。REAP基于Mistral-Small-24B-Instruct-2501模型构建,在测试集上取得了0.62的宏观F1分数,在countryLandBordersCountry和companyTradesAtStockExchange等特定关系类型上表现强劲。 AI

影响 这项研究展示了一种从大型语言模型中提取结构化知识的方法,有望提高特定领域知识库创建的准确性和效率。

排序理由 该集群描述了一篇研究论文,详细介绍了一个用于从大型语言模型构建知识库的系统,包括具体的性能指标和模型细节。[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 →

REAP系统从大型语言模型中提取知识,用于AKBC共享任务2026

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一篇研究论文,详细介绍了一个用于从大型语言模型构建知识库的系统,包括具体的性能指标和模型细节。[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
68 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Thanh-Dan Bui, Thanh-Trung Do, Tuan-Phong Nguyen ·

    REAP: 用于从大型语言模型构建闭卷知识库的关系感知提取与解析

    arXiv:2608.10963v1 Announce Type: new Abstract: We present the REAP system for the AKBC Shared Task 2026 on constructing knowledge bases from language models in a closed-book setting, subject to a budget of at most 32B parameters and no model fine-tuning. Our system combines stru…