EAGER: Knowledge-guided neurosymbolic AI with guardrails for safe virtual health assistants
EAGER:知识引导的神经符号人工智能,带有安全虚拟健康助手的护栏
基本信息
- 批准号:2335967
- 负责人:
- 金额:$ 20万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2023
- 资助国家:美国
- 起止时间:2023-10-01 至 2025-09-30
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
This project addresses the limitations of generative artificial intelligence (AI) systems, particularly in the context of virtual assistants used to support healthcare (VHAs). While VHAs show potential for empowering patients and addressing clinical expertise shortages, concerns about safety and accessibility arise due to inaccuracies in their outputs and their lack of adherence to the relevant standards of care. To mitigate these concerns, the project proposes an innovative approach for integrating clinical protocols and practice guidelines within AI systems. This approach will enable the development of safety constrained VHAs that support clinicians and ensure safe interactions with patients. Additionally, the approach facilitates the provision of clinician-friendly explanations, fostering improved collaboration between humans and AI in healthcare. By addressing significant current concerns surrounding the safety of generative AI, the research will promote user confidence and adoption in safety-critical domains requiring human-AI collaboration. The research's success can have implications beyond healthcare, such as autonomous vehicles incorporating traffic rules or manufacturing processes ensuring safe operations and maintenance compliance. Furthermore, the project aligns with efforts to promote inclusivity in computing, workforce development, and education. Example initiatives include annual AI summer camp for school students from underrepresented backgrounds, and engagement with high school, undergraduate and graduate students through internships and workforce development modules relevant to interdisciplinary AI careers.The main innovation of this research lies in leveraging Knowledge Graphs (KGs) to construct guardrails that help ensure the safety of AI systems. In collaboration with clinical experts, a KG enriched with both declarative (e.g., medical terminology and definitions) and procedural or process knowledge (e.g., diagnostic criteria and clinical practice guidelines) will be employed to guide neural processing architectures, resulting in the development of VHAs inherently constrained to be safe. Furthermore, the same proposed methods will also equip VHAs with the ability to generate end user (e.g., clinician) friendly explanations making the system verifiable. The project's two important outcomes will be to (a) effectively apply medical guidelines from the KG to uphold high safety standards in a clinical setting, and (b) generate explanations that are easily comprehensible to end users using the terms, concepts, and guidelines relevant to end-user verification and decision-making. The core techniques proposed in this project will advance the state-of-the-art in neurosymbolic AI toward facilitating robust (verifiable and safety-constrained) collaboration between humans and AI. These advances have the potential for transferability to other domains with safety-critical applications, thus contributing to the broader field of AI research and its wider adoption.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
该项目解决了生成人工智能(AI)系统的局限性,特别是在用于支持医疗保健(VHA)的虚拟助理的背景下。虽然VHA显示出增强患者能力和解决临床专业知识短缺的潜力,但由于其输出不准确以及缺乏对相关护理标准的遵守,人们对安全性和可及性表示担忧。为了缓解这些担忧,该项目提出了一种创新的方法,将临床协议和实践指南整合到人工智能系统中。这种方法将能够开发安全受限的VHA,以支持临床医生并确保与患者的安全互动。此外,该方法有助于提供对临床医生友好的解释,促进人类与人工智能在医疗保健领域的合作。通过解决当前围绕生成式人工智能安全性的重大问题,该研究将促进用户在需要人类-人工智能协作的安全关键领域的信心和采用。该研究的成功可能会产生超出医疗保健范围的影响,例如自动驾驶汽车纳入交通规则或确保安全操作和维护合规性的制造过程。此外,该项目与促进计算,劳动力发展和教育包容性的努力保持一致。例如,为来自代表性不足背景的学生举办的年度人工智能夏令营,以及通过实习和与跨学科人工智能职业相关的劳动力发展模块与高中生、本科生和研究生进行互动。这项研究的主要创新在于利用知识图(KGs)构建护栏,帮助确保人工智能系统的安全。在与临床专家的合作下,一个既有陈述性(例如,医学术语和定义)和程序或过程知识(例如,诊断标准和临床实践指南)将用于指导神经处理架构,导致VHA的开发本质上受到安全性的限制。此外,所提出的相同方法还将使VHA具有生成最终用户(例如,临床医生)友好的解释,使系统可验证。该项目的两个重要成果将是:(a)有效应用幼儿园的医疗指南,以在临床环境中坚持高安全标准,以及(B)使用与最终用户验证和决策相关的术语、概念和指南,生成最终用户易于理解的解释。该项目提出的核心技术将推动神经符号AI的发展,促进人类和AI之间的强大(可验证和安全约束)协作。这些进步有可能转移到其他领域的安全关键应用,从而有助于更广泛的人工智能研究领域及其更广泛的采用。该奖项反映了NSF的法定使命,并被认为值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估来支持。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Amit Sheth其他文献
Grounding From an AI and Cognitive Science Lens
从人工智能和认知科学的角度出发
- DOI:
10.1109/mis.2024.3366669 - 发表时间:
2024 - 期刊:
- 影响因子:6.4
- 作者:
Goonmeet Bajaj;V. Shalin;Srinivasan Parthasarathy;Amit Sheth;Amit Sheth - 通讯作者:
Amit Sheth
Causal Event Graph-Guided Language-based Spatiotemporal Question Answering
因果事件图引导的基于语言的时空问答
- DOI:
- 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Kaushik Roy;Alessandro Oltramari;Yuxin Zi;Chathurangi Shyalika;Vignesh Narayanan;Amit Sheth - 通讯作者:
Amit Sheth
Cognitive manufacturing: definition and current trends
- DOI:
10.1007/s10845-024-02429-9 - 发表时间:
2024-06-20 - 期刊:
- 影响因子:7.400
- 作者:
Fadi El Kalach;Ibrahim Yousif;Thorsten Wuest;Amit Sheth;Ramy Harik - 通讯作者:
Ramy Harik
Ki-Cook: Clustering Multimodal Cooking Representations Through Ki-Cook: Clustering Multimodal Cooking Representations Through Knowledge-infused Learning Knowledge-infused Learning
Ki-Cook:通过知识注入学习对多模态烹饪表示进行聚类 Ki-Cook:通过知识注入学习对多模态烹饪表示进行聚类 知识注入学习
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
Thommen Karimpanal George;R. Venkataramanan;Swati Padhee;Saini Rohan;Rao Ronak;Anirudh Kaoshik 4;Sundara Rajan;Amit Sheth - 通讯作者:
Amit Sheth
RDR: the Recap, Deliberate, and Respond Method for Enhanced Language Understanding
RDR:增强语言理解的回顾、深思熟虑和回应方法
- DOI:
- 发表时间:
2023 - 期刊:
- 影响因子:0
- 作者:
Yuxin Zi;Hariram Veeramani;Kaushik Roy;Amit Sheth - 通讯作者:
Amit Sheth
Amit Sheth的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Amit Sheth', 18)}}的其他基金
EAGER: Advancing Neuro-symbolic AI with Deep Knowledge-infused Learning
EAGER:通过深度知识注入学习推进神经符号人工智能
- 批准号:
2133842 - 财政年份:2021
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
NSF Convergence Accelerator: Symposium on Big Data and AI-Driven Disaster Management for Planning, Response, Recovery, and Resiliency
NSF 融合加速器:大数据和人工智能驱动的灾害管理规划、响应、恢复和复原力研讨会
- 批准号:
1956285 - 财政年份:2020
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
TWC SBE: Medium: Context-Aware Harassment Detection on Social Media
TWC SBE:媒介:社交媒体上的情境感知骚扰检测
- 批准号:
2013801 - 财政年份:2019
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
Spokes: MEDIUM: MIDWEST: Collaborative: Community-Driven Data Engineering for Substance Abuse Prevention in the Rural Midwest
辐条:媒介:中西部:协作:社区驱动的数据工程,用于中西部农村地区的药物滥用预防
- 批准号:
1956009 - 财政年份:2019
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
Spokes: MEDIUM: MIDWEST: Collaborative: Community-Driven Data Engineering for Substance Abuse Prevention in the Rural Midwest
辐条:媒介:中西部:协作:社区驱动的数据工程,用于中西部农村地区的药物滥用预防
- 批准号:
1761931 - 财政年份:2018
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
III: Travel Fellowships for Students from U.S. Universities to Attend ISWC 2016
三:美国大学学生参加 ISWC 2016 的旅费奖学金
- 批准号:
1622628 - 财政年份:2016
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
PFI:AIR - TT: Market Driven Innovations and Scaling up of Twitris- A System for Collective Social Intelligence
PFI:AIR - TT:市场驱动的创新和 Twitris 的扩展——集体社交智能系统
- 批准号:
1542911 - 财政年份:2015
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
TWC SBE: Medium: Context-Aware Harassment Detection on Social Media
TWC SBE:媒介:社交媒体上的情境感知骚扰检测
- 批准号:
1513721 - 财政年份:2015
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
I-Corps: Towards Commercialization of Twitris- a system for collective intelligence
I-Corps:迈向 Twitris 的商业化——集体智慧系统
- 批准号:
1343041 - 财政年份:2013
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
SoCS: Collaborative Research: Social Media Enhanced Organizational Sensemaking in Emergency Response
SoCS:协作研究:社交媒体增强应急响应中的组织意识
- 批准号:
1111182 - 财政年份:2011
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
相似海外基金
Collaborative Research: MRA: Advancing process understanding of lake water quality to macrosystem scales with knowledge-guided machine learning
合作研究:MRA:通过知识引导的机器学习将湖泊水质的过程理解推进到宏观系统尺度
- 批准号:
2213549 - 财政年份:2022
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
CAREER: Toward A Knowledge-Guided Framework for Personalized Decision Making
职业:走向个性化决策的知识引导框架
- 批准号:
2144209 - 财政年份:2022
- 资助金额:
$ 20万 - 项目类别:
Continuing Grant
Collaborative Research: MRA: Advancing process understanding of lake water quality to macrosystem scales with knowledge-guided machine learning
合作研究:MRA:通过知识引导的机器学习将湖泊水质的过程理解推进到宏观系统尺度
- 批准号:
2213550 - 财政年份:2022
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
HDR Institute: Imageomics: A New Frontier of Biological Information Powered by Knowledge-Guided Machine Learning
HDR 研究所:图像组学:知识引导机器学习驱动的生物信息新领域
- 批准号:
2118240 - 财政年份:2021
- 资助金额:
$ 20万 - 项目类别:
Cooperative Agreement
III: Medium: Knowledge-Guided Meta Learning for Multi-Omics Survival Analysis
III:媒介:用于多组学生存分析的知识引导元学习
- 批准号:
2106913 - 财政年份:2021
- 资助金额:
$ 20万 - 项目类别:
Continuing Grant
CRII: III: Disciplinary Knowledge Guided Big Spatial Structured Models for Geoscience Applications
CRII:III:学科知识引导的地球科学应用大空间结构化模型
- 批准号:
2147908 - 财政年份:2021
- 资助金额:
$ 20万 - 项目类别:
Standard Grant
Design model for the knowledge-based adjustment of the edge zone and surface properties of additive-manufactured components for guided centrifugal finishing
用于基于知识调整增材制造部件边缘区域和表面特性的设计模型,用于引导离心精加工
- 批准号:
429960079 - 财政年份:2020
- 资助金额:
$ 20万 - 项目类别:
Research Grants
Development, evaluation, and implementation of a pediatric shared decision making program: a knowledge translation initiative guided by the Knowledge to Action Framework
儿科共享决策计划的开发、评估和实施:以知识到行动框架为指导的知识转化计划
- 批准号:
421859 - 财政年份:2020
- 资助金额:
$ 20万 - 项目类别:
Collaborative Research: Knowledge Guided Machine Learning: A Framework for Accelerating Scientific Discovery
协作研究:知识引导机器学习:加速科学发现的框架
- 批准号:
1934633 - 财政年份:2019
- 资助金额:
$ 20万 - 项目类别:
Continuing Grant
Collaborative Research: Knowledge Guided Machine Learning: A Framework for Accelerating Scientific Discovery
协作研究:知识引导机器学习:加速科学发现的框架
- 批准号:
1934721 - 财政年份:2019
- 资助金额:
$ 20万 - 项目类别:
Continuing Grant