11-19 更新 实时
首页/ 算力/ 正文

研究人员开发以人为本的AI供应商选择框架

算力 来源:TechXplore 2026-11-17 20:20 0 阅读 机器翻译
研究人员开发以人为本的AI供应商选择框架

继续使用 Google、Facebook 或 Apple,即表示你同意使用条款。

研究人员开发出由 AI 驱动、以人为本的供应商选择框架

作者:Adrian Chalifour,Constructor University

编辑:Sadie Harley,审阅:Andrew Zinin

本文已按照 Science X 的编辑流程与政策进行审核。编辑在确保内容可信度的同时,重点指出了以下属性:

添加到首选来源

随着全球供应链面临日益复杂且难以预测的社会经济、环境和监管条件,许多企业对快速、有效的供应商评估的需求不断上升。为解决这一问题,Constructor University 的一组研究人员提出了一种新的供应商选择框架,将大语言模型(LLM)AI 的解读能力与人工监督相结合,以改善供应商评估结果。

尽管供应商选择传统上依赖成本、质量和交付表现等核心因素,但如今的采购团队往往还必须将可持续性、监管合规、运营风险、韧性以及不断变化的市场条件等许多其他要求纳入考量。

由 Constructor University 工业工程新兴技术(EITIE)研究组的工业工程教授 Fatahi Valilai 博士、博士研究员 Mohammadreza Rezaei 和硕士生 Sridhar Sreemulnath Iyer 开发的新框架,通过提出在 AI、基于规则的分析系统与人工监督之间进行互补的责任划分,来应对这种复杂性。

该研究成果发表在期刊 Machine Learning with Applications 上。

Fatahi Valilai 表示:“这项研究的动因来自我们在新兴技术工作中越来越频繁遇到的一个问题:我们如何既能受益于 AI 的灵活性和推理能力,又不必在工业决策中放弃透明度、可追溯性和人的责任?”

“因此,我们的研究转向智能体式和声明式决策架构:在这种架构中,AI 可以解读不断变化的条件并提出可能的行动方案,而明确的分析规则和人类治理则决定实际实施的内容。”

该框架提出在整个流程中利用 LLM 来解读采购请求、对供应商提供的证据进行结构化处理和分析,并用自然语言解释结果。

这一角色由关键阶段的人工监督与干预加以补充,从而既能发挥 AI 的速度、规模和算力,又能保留人类对假设、证据以及最终影响结果的决策所承担的责任。

Rezaei 表示:“这项研究背后的一个核心洞见是,AI 在采购中的价值不仅取决于它能处理多少信息,还取决于决策者能否理解、审查并负责任地依赖它的输出。”

“因此,我们围绕清晰的职责划分来设计该框架。在已有成熟确定性方法的地方,我们保留这些方法用于数值评分、约束执行和供应商排名。”

该框架包含四个检查点,需由人类采购专业人员完成:

批准底层数据

审核场景与权重设置

评估证据的相关性,以及

授权最终决策。

对框架进行测试

作为该项目的一部分,研究团队通过将该框架回溯应用于 22,230 个历史欧洲公共采购案例的记录,来评估该框架,以查看最初选定的供应商出现在该框架生成的排名最高结果中的频率。

他们发现,当数据中纳入更多与采购相关的特定背景信息时,排名的吻合度会大幅提高,这些信息包括供应商在相关品类中的经验、地理适宜性以及与买方的既往合作关系。

在这些情景下,原本中标成功的供应商约有 32% 的情况能进入该框架的前 10 名,而在仅考虑更通用的供应商特征时,这一比例仅为 5%。这一提升表明,当供应商排名反映出采购情境的具体情况、而非仅依据一般性活动时,其信息价值会大得多。

团队还对这款 LLM 进行了评估,确定其有效结构化输出率为 1.000,意味着它始终以要求的格式返回信息。它同时取得了 0.928 的证据抽取 F1 分数均值,表明其在识别和抽取所分析供应商文件中的相关主张方面表现强劲。

最后,研究人员测试了 LLM 能否在不改变排名的情况下一致地解释排名。在每一个解释案例中,模型都保留了该框架确定的固定排名,这表明它可以帮助传达已完成分析背后的推理过程,而不会接管计算或在暗中改变结果。

综合来看,这些发现支持该框架的职责划分:AI 高效地解读和整理信息并解释结果,预先编程的分析工具生成固定的分数和排名,而人类采购专业人员则审查证据并对重大决策予以批准。

实验还发现了若干局限性,这些局限性进一步印证了人工审核的必要性,尤其在证据不完整、相互矛盾或带有保留条件时更是如此。

Mohammadreza Rezaei 等,一种结合大语言模型与人工监督的受治理框架用于供应商选择,Machine Learning with Applications(2026)。DOI: 10.1016/j.mlwa.2026.101028

这篇报道背后是谁?

生命科学与生态学学士。拥有微生物学实验室背景,以及石油、天然气和可再生能源行业的医药新闻经验。完整简介 →

物理学硕士,具备研究经历。长期的科学新闻爱好者。在 Science X 的编辑工作成功中发挥关键作用。完整简介 →

引用:研究人员开发出由 AI 驱动、以人为本的供应商选择框架(2026年11月17日),检索于 2026年11月17日,来自 https://techxplore.com/news/2026-11-ai-powered-human-centered-framework.html

本文件受版权保护。除为私人学习或研究目的进行的合理使用外,未经书面许可不得复制任何部分。内容仅供参考。

研究表明,AI 的广泛采用掩盖了更深层的问题

团队提出一个推理框架,旨在提升 LLM 的可靠性与可追溯性

研究发现 AI 可以安全地辅助部分软件标注任务

研究人员为欧盟《人工智能法案》提供 LLM 基准测试套件

新方法能以高准确率预测 LLM 在未经尝试任务上的成功表现

基于对话的 AI 让用户能在自己的电脑上运行复杂的合金计算

研究估算美国数据中心污染的规模,与此同时气候谈判公布清洁 AI 承诺

衡量 GitHub 热度或可揭示哪些软件缺陷需要优先修复

人类与机器人共用的信号:柔性显示屏同时利用颜色和近红外进行通信

“超级跑鞋”为何如此快?

获取即时摘要文本(Gist)

供应商选择框架结合了 LLM 证据处理、确定性排序和人工审核。在 22,230 个历史采购案例中,采购特定上下文将原始中标者进入前 10 的比例从 5% 提高到 32%。证据提取 F1 为 0.928;不完整或相互矛盾的证据仍需人工审核。

本摘要使用 LLM 自动生成。完整免责声明

译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。

查看英文原文(Researchers develop AI-powered, human-centered framework for supplier selection)

By continuing with Google, Facebook or Apple, you agree to the Terms of Use.

Researchers develop AI-powered, human-centered framework for supplier selection

by Adrian Chalifour, Constructor University

edited by Sadie Harley, reviewed by Andrew Zinin

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

Add to Preferred Sources

supply chain Credit: Unsplash/CC0 Public Domain

With global supply chains facing increasingly complex and unpredictable socio-economic, environmental and regulatory conditions, many companies are facing a growing need for quick and effective supplier evaluation. To address this concern, a group of researchers at Constructor University have proposed a new supplier selection framework that combines the interpretive power of large language model (LLM) AI with human oversight to improve supplier outcomes.

While supplier selection has traditionally relied on core factors like cost, quality and delivery performance, procurement teams today must often factor in many other requirements such as sustainability, regulatory compliance, operational risk, resilience and changing market conditions.

The new framework developed by industrial engineering Professor Dr. Fatahi Valilai, Ph.D. researcher Mohammadreza Rezaei and master's student Sridhar Sreemulnath Iyer at Constructor University's Emerging Technologies in Industrial Engineering (EITIE) research group addresses this complexity by proposing a complementary division of responsibility between AI, rule-based analytical systems and human oversight.

The work is published in the journal Machine Learning with Applications.

"This research was motivated by a question we see arising more and more across our work in emerging technologies: How can we benefit from the flexibility and reasoning capabilities of AI without giving up transparency, traceability and human responsibility in industrial decision-making?" said Fatahi Valilai.

"Our work therefore moves toward agentic and declarative decision architectures in which AI can interpret changing conditions and formulate possible actions, while explicit analytical rules and human governance determine what is actually implemented."

The framework proposes leveraging the LLM throughout the process to interpret procurement requests, structure and analyze evidence provided by suppliers, and explain the results using natural language.

This role is complemented by human oversight and intervention at key stages, allowing the speed, scale and processing power of AI to be harnessed while still preserving human accountability for the assumptions, evidence and, ultimately, decisions that inform the final outcome.

"A central insight behind this research is that the value of AI in procurement depends not only on how much information it can process, but also on whether decision-makers can understand, examine and responsibly rely on its outputs," said Rezaei.

"We therefore designed the framework around a clear division of responsibilities. Where established deterministic methods already exist, we retain them for numerical scoring, constraint enforcement and supplier ranking."

The framework incorporates four checkpoints to be completed by human procurement professionals:

Approving the underlying data

Reviewing scenarios and weighting

Assessing the relevance of evidence, and

Authorizing the final decision.

Putting the framework to the test

As part of the project, the research team evaluated the framework by applying it retroactively to records of 22,230 historical European public procurement cases to see how often the originally selected supplier appeared in the top-ranked results produced by the framework.

They found that rankings became much more closely aligned when additional, procurement-specific context was included in the data, such as supplier experience in the relevant category, geographic suitability and a previous relationship with the buyer.

In these scenarios, the original successful supplier ranked in the framework's top 10 about 32% of the time, compared to just 5% of the time when a more general set of supplier characteristics was considered. This increase suggests that supplier rankings become far more informative when they reflect the specifics of a procurement situation rather than general activity alone.

The team also assessed the LLM and determined it had a valid structured-output rate of 1.000, meaning it consistently returned information in the required format. It also achieved a mean evidence-extraction F1 score of 0.928, indicating a strong performance at identifying and extracting relevant claims from the supplier documents it analyzed.

Finally, the researchers tested whether the LLM could consistently explain rankings without changing them. In every explanation case, the model preserved the fixed rankings established by the framework, which suggests that it could help communicate the reasoning behind completed analysis without taking over the calculation or silently altering the result.

Taken together, the findings support the framework's division of responsibilities, with the AI efficiently interpreting and organizing information and explaining results, programmed analytical tools producing fixed scores and rankings, and human procurement professionals reviewing the evidence and approving consequential decisions.

The experiments also identified limitations that reinforce the need for human review, particularly when evidence is incomplete, conflicting or qualified.

Mohammadreza Rezaei et al., A governed framework combining large language models and human oversight for supplier selection, Machine Learning with Applications (2026). DOI: 10.1016/j.mlwa.2026.101028

Who's behind this story?

Sadie Harley

BSc Life Sciences & Ecology. Microbiology lab background with pharmaceutical news experience in oil, gas, and renewable industries. Full profile →

Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile →

Citation: Researchers develop AI-powered, human-centered framework for supplier selection (2026, November 17) retrieved 17 November 2026 from https://techxplore.com/news/2026-11-ai-powered-human-centered-framework.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Widespread AI adoption masks deeper problem, study shows

Team proposes a reasoning framework aimed at improving the reliability and traceability of LLMs

Study finds AI can safely assist with some software annotation tasks

Researchers provide LLM benchmarking suite for the EU Artificial Intelligence Act

New method predicts the success of LLMs on untried tasks with high accuracy

Chat-based AI lets users run complex alloy calculations on their own computers

Credit without debit: A new way for hackers to target bank accounts

Study estimates magnitude of US data center pollution as climate talks unveil clean AI pledge

Measuring GitHub popularity could reveal which software flaws need fixes first

A shared signal for humans and robots: Flexible display uses both color and near-infrared to communicate

What makes 'super shoes' so fast?

Get Instant Summarized Text (Gist)

A supplier-selection framework combines LLM evidence processing, deterministic ranking and human review. In 22,230 historical procurement cases, procurement-specific context increased top-10 inclusion of the original winner from 5% to 32%. Evidence-extraction F1 was 0.928; incomplete or conflicting evidence still required human review.

This summary was automatically generated using LLM. Full disclaimer

This site uses cookies to assist with navigation, analyse your use of our services, collect data for ads personalisation and provide content from third parties. By using our site, you acknowledge that you have read and understand our Privacy Policy and Terms of Use.

原文为英文,正文由自动抓取并保留原文。

本文由采集器自动同步

原文发布于 TechXplore(Researchers develop AI-powered, human-centered framework for supplier selection),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。

阅读原文 ↗