An Updated Duet Model for Passage Re-ranking
Bhaskar Mitra, Nick Craswell
Abstract
We propose several small modifications to Duet---a deep neural ranking model---and evaluate the updated model on the MS MARCO passage ranking task. We report significant improvements from the proposed changes based on an ablation study.
Results
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Passage Re-Ranking | MS MARCO | MRR | 0.253 | Duet v2 |
Related Papers
Overview of the TalentCLEF 2025: Skill and Job Title Intelligence for Human Capital Management2025-07-17MCoT-RE: Multi-Faceted Chain-of-Thought and Re-Ranking for Training-Free Zero-Shot Composed Image Retrieval2025-07-17CATVis: Context-Aware Thought Visualization2025-07-15SAMURAI: Shape-Aware Multimodal Retrieval for 3D Object Identification2025-06-26IRanker: Towards Ranking Foundation Model2025-06-25RAG-VisualRec: An Open Resource for Vision- and Text-Enhanced Retrieval-Augmented Generation in Recommendation2025-06-25RMIT-ADM+S at the SIGIR 2025 LiveRAG Challenge2025-06-17SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement2025-06-16