Author

Shlomit Plavner

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Listwise Cross-Encoder Fine-Tuning vs. Agentic Instruction Tuning for LLM Rerankers: A Systematic Study in Medical Procedure Reranking

A systematic comparison of two reranking paradigms for this production task finds that a 109M-parameter cross-encoder fine-tuned with ListNet outperforms the 4B-parameter model by 2.6 percentage points on NDCG@3 and 13.3 points on Spearman correlation - at 37x fewer parameters.

M. Fainzilber, Shlomit Plavner · 0 citations