Fine-tuned MedCPT cross-encoders beat a prompt-optimized 4B instruction reranker by 2.6 NDCG@3 points and 13.3 Spearman points on an AI-generated medical procedure ranking benchmark.
Proceedings of the 2nd Clinical Natural Language Processing Workshop , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Listwise Cross-Encoder Fine-Tuning vs. Agentic Instruction Tuning for LLM Rerankers: A Systematic Study in Medical Procedure Reranking
Fine-tuned MedCPT cross-encoders beat a prompt-optimized 4B instruction reranker by 2.6 NDCG@3 points and 13.3 Spearman points on an AI-generated medical procedure ranking benchmark.