---
title: "使用LLM辅助工具和溯源知识图谱管理随机临床试验出版物的透明研究诚信评估"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.07202v1"
permalink: "https://feed.astralor.com/items/itm_1af1ff0ee98e97cb4d70b73d"
published: "2026-08-07T13:17:56.000Z"
score: 72
channel: "tech"
tags: ["INSPECT-AI","LLM","知识图谱","研究诚信"]
---

# 使用LLM辅助工具和溯源知识图谱管理随机临床试验出版物的透明研究诚信评估

## AI 点评

> 这项研究为医疗证据审查提供了 AI 辅助方案，对医学信息学、临床研究方法学以及 LLM 应用研究者都很有价值。虽然目前只是预印本，但 RIPE-KG 数据集可能成为后续研究的重要基础。

## 速览

该论文介绍INSPECT-AI，一个基于LLM的交互式工具，帮助人类评审员根据INSPECT-SR框架对已发表的随机对照试验（RCT）进行研究诚信评估，并使用RIPE-O本体记录评估过程溯源。同时，论文发布RIPE-KG，一个包含140条专家评估、覆盖95篇RCT出版物的知识图谱，旨在提高系统综述证据的可靠性和透明度。

## 关键点

- INSPECT-AI 结合 LLM 与溯源知识图谱，辅助人工评审员进行 RCT 研究诚信评估。
- 采用 RIPE-O 本体记录评估过程的溯源信息，提升评审透明度。
- RIPE-KG 包含 140 条专家评估，覆盖 95 篇 RCT 出版物。
- 旨在减少人工评估负担，提高评审一致性与证据质量。

## 全文

Systematic reviews of Randomised Controlled Trials (RCTs) are routinely used as evidence for clinical care guidelines. Such evidence has to meet high research integrity standards to prevent low quality or false research outputs influencing the clinical care. However, assessing research integrity of published RCTs is a complex process requiring manual effort, and potentially resulting in diverse opinions of the human assessors. This paper describes INSPECT-AI, an LLM-based interactive tool that assists human reviewers with research integrity assessments of published RCTs based on the community approved INSPECT-SR framework, and the Research Integrity Provenance and Evidence ontology (RIPE-O) for documenting the provenance of the assessment process. In addition, we present the Research Integrity Provenance and Evidence knowledge graph (RIPE-KG), an initial set of 140 expert research integrity assessments of 95 RCT publications generated by INSPECT-AI and described using RIPE-O.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_1af1ff0ee98e97cb4d70b73d