Correspondences as Decisions: JevNexus for Decision-Centric Schema Matching
We present JevNexus, which combines typed pairwise decisions with schema/instance evidence and invokes listwise refinement only when the evidence disagrees and the fused margin is small.
ProofPaper ↗
Key points
- Schema matching increasingly uses generative language models to rerank retrieved column candidates, although the underlying task is a bounded correspondence decision.
- The evaluation covers 561 cases from six benchmark families.
- JevNexus obtains dataset-macro MRR and Hits@1 of 0.930 and 0.909, compared with 0.926 and 0.903 for Magneto, while reducing mean latency from 123.452 to 15.929 seconds (7.750).
- Paired analysis finds no statistically significant difference in either MRR or Hits@1.
Sources (1)
- [1]Correspondences as Decisions: JevNexus for Decision-Centric Schema MatchingarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 05:42 AM
We present JevNexus, which combines typed pairwise decisions with schema/instance evidence and invokes listwise refinement only when the evidence disagrees and the fused margin is small.
Schema matching increasingly uses generative language models to rerank retrieved column candidates, although the underlying task is a bounded correspondence decision.
Extractive summary: sentences quoted from the sources.