PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 1, 2026Electronics0 citationsOpen Access

LLM-Enhanced Semantic Augmentation for Temporal Knowledge Graph Reasoning

LLM-DSaR: LLM-Enhanced Semantic Augmentation for Temporal Knowledge Graph Reasoning

View Full Paper
Ask AI
Bookmark
Share

Authors

RLRuoxi LiuCLChunfang LiuXZXun Zhang

Discussion

Loading...

Member takes

Overview

A model improves temporal knowledge graph inference accuracy, indicating better decision-making capabilities in complex domains.

Key Points

  • The aim is to enhance temporal knowledge graph inference by addressing modeling and reasoning challenges in dynamic contexts.
  • Developed a two-stage LLM semantic enhancement framework.
  • Generated semantic analysis reports through adaptive prompt engineering.
  • Utilized dynamic weight fusion to adaptively assign feature weights.
  • Implemented an LLM-enhanced contrastive-learning module to improve clustering and discrimination.
  • LLM-DSaR achieved 10.35 percentage points higher MRR compared to GCR on the Robotics Temporal Knowledge Graph.
  • Hits@10 reached 88.87%, outperforming 16 baseline models.
  • Core modules were validated for effectiveness through ablation experiments.

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/69ccb72e16edfba7beb89102https://doi.org/10.3390/electronics15071446
View Full Paper
Ask AI
Bookmark
Share