Zero-Shot NLI Stance Detection for Knowledge Graph Edge Classification: Validating the Inference Level

Radboud University Nijmegen

Indexed indatacite

Abstract

Paper 1 in the Prioris research series. Validates inference-level edge classification using mDeBERTa-v3 zero-shot NLI for CONFIRMS and CONTRADICTS edges. Compares against Claude Haiku and fine-tuned BERT baselines across three domains and two languages. Part of the Evidence-Graded Knowledge Graphs research programme (Paper 0: 10.5281/zenodo.19024611).

Citation impact

12
total citations
FWCI
Percentile
References
0
Too recent for citation history.

Authors

1

Topics & keywords

Keywords
  • Inference
  • Graph
  • Knowledge graph
  • Enhanced Data Rates for GSM Evolution
  • General knowledge
  • Pattern recognition (psychology)
UN Sustainable Development Goals
  • Quality Education
No related works found for this paper.