View in EDS HTML Full Text PDF Full Text

A Prior-Guided Adaptive Framework for Table Reasoning in Power Grid Material Management.

Saved in:
Bibliographic Details
Title: A Prior-Guided Adaptive Framework for Table Reasoning in Power Grid Material Management.
Authors: Yang, Yaming1 (AUTHOR), Xu, Maolin1,2 (AUTHOR), Ma, Wanyi1 (AUTHOR), Wei, Bo1,2 (AUTHOR), Liu, Kangjun1 (AUTHOR), Huang, Siping1 (AUTHOR), Liang, Chuheng1 (AUTHOR), Yuan, Shiyi1 (AUTHOR), Chen, Mingyi2 (AUTHOR), Li, Xiaoxin2 (AUTHOR) lixiaoxin@sz.tsinghua.edu.cn
Source: Energies (19961073). May2026, Vol. 19 Issue 10, p2396. 30p.
Subject Terms: *Materials management, *Data fusion (Statistics), *Digital transformation, *Knowledge base, *Electric power distribution grids, *Software frameworks, *Machine learning
Abstract: With the digital transformation of smart grids, power material management uses massive heterogeneous data, including structured procurement tables and unstructured demand texts. Existing multimodal models like TAMO fuse tabular and textual modalities to solve data silos, yet their static hard fusion brings extra noise. This paper proposes AdaTAMO, a prior-guided adaptive framework based on TAMO, with three core contributions. At the model level, it designs a domain knowledge-driven adaptive gating mechanism, using heuristic semantic rules to dynamically fuse text and table modalities on demand, reducing noise. At the data level, it builds Power-TableQA, a dedicated dataset for power material reasoning; the full dataset is private for compliance, but its construction pipeline and prompt templates are open-sourced for reproducibility. At the application level, it presents power grid material management scenarios and clarifies the model's integration path. Experiments show that AdaTAMO performs comparably or better on general datasets, and outperforms baselines on the domain dataset, with higher query accuracy and interpretability for material demand decision making. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 194141511
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A Prior-Guided Adaptive Framework for Table Reasoning in Power Grid Material Management.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yang%2C+Yaming%22">Yang, Yaming</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xu%2C+Maolin%22">Xu, Maolin</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ma%2C+Wanyi%22">Ma, Wanyi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wei%2C+Bo%22">Wei, Bo</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Kangjun%22">Liu, Kangjun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Huang%2C+Siping%22">Huang, Siping</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liang%2C+Chuheng%22">Liang, Chuheng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yuan%2C+Shiyi%22">Yuan, Shiyi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chen%2C+Mingyi%22">Chen, Mingyi</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Xiaoxin%22">Li, Xiaoxin</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> lixiaoxin@sz.tsinghua.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energies+%2819961073%29%22">Energies (19961073)</searchLink>. May2026, Vol. 19 Issue 10, p2396. 30p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Materials+management%22">Materials management</searchLink><br />*<searchLink fieldCode="DE" term="%22Data+fusion+%28Statistics%29%22">Data fusion (Statistics)</searchLink><br />*<searchLink fieldCode="DE" term="%22Digital+transformation%22">Digital transformation</searchLink><br />*<searchLink fieldCode="DE" term="%22Knowledge+base%22">Knowledge base</searchLink><br />*<searchLink fieldCode="DE" term="%22Electric+power+distribution+grids%22">Electric power distribution grids</searchLink><br />*<searchLink fieldCode="DE" term="%22Software+frameworks%22">Software frameworks</searchLink><br />*<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: With the digital transformation of smart grids, power material management uses massive heterogeneous data, including structured procurement tables and unstructured demand texts. Existing multimodal models like TAMO fuse tabular and textual modalities to solve data silos, yet their static hard fusion brings extra noise. This paper proposes AdaTAMO, a prior-guided adaptive framework based on TAMO, with three core contributions. At the model level, it designs a domain knowledge-driven adaptive gating mechanism, using heuristic semantic rules to dynamically fuse text and table modalities on demand, reducing noise. At the data level, it builds Power-TableQA, a dedicated dataset for power material reasoning; the full dataset is private for compliance, but its construction pipeline and prompt templates are open-sourced for reproducibility. At the application level, it presents power grid material management scenarios and clarifies the model's integration path. Experiments show that AdaTAMO performs comparably or better on general datasets, and outperforms baselines on the domain dataset, with higher query accuracy and interpretability for material demand decision making. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=194141511
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/en19102396
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 30
        StartPage: 2396
    Subjects:
      – SubjectFull: Materials management
        Type: general
      – SubjectFull: Data fusion (Statistics)
        Type: general
      – SubjectFull: Digital transformation
        Type: general
      – SubjectFull: Knowledge base
        Type: general
      – SubjectFull: Electric power distribution grids
        Type: general
      – SubjectFull: Software frameworks
        Type: general
      – SubjectFull: Machine learning
        Type: general
    Titles:
      – TitleFull: A Prior-Guided Adaptive Framework for Table Reasoning in Power Grid Material Management.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yang, Yaming
      – PersonEntity:
          Name:
            NameFull: Xu, Maolin
      – PersonEntity:
          Name:
            NameFull: Ma, Wanyi
      – PersonEntity:
          Name:
            NameFull: Wei, Bo
      – PersonEntity:
          Name:
            NameFull: Liu, Kangjun
      – PersonEntity:
          Name:
            NameFull: Huang, Siping
      – PersonEntity:
          Name:
            NameFull: Liang, Chuheng
      – PersonEntity:
          Name:
            NameFull: Yuan, Shiyi
      – PersonEntity:
          Name:
            NameFull: Chen, Mingyi
      – PersonEntity:
          Name:
            NameFull: Li, Xiaoxin
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 05
              Text: May2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 19961073
          Numbering:
            – Type: volume
              Value: 19
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Energies (19961073)
              Type: main
ResultId 1