Cross-encoders fine-tuned from Transformer backbones remain the standard for second-stage re-ranking, and recent knowledge-distillation strategies have closed much of the gap with LLM re-rankers. H...
<p><strong>Tác giả:</strong> Victor Morand, Mathias Vast, Basile Van Cooten, Laure Soulier, Josiane Mothe, Benjamin Piwowarski</p>
<p>Cross-encoders fine-tuned from Transformer backbones remain the standard for second-stage re-ranking, and recent knowledge-distillation strategies have closed much of the gap with LLM re-rankers. However, these strategies have not been compared under controlled conditions. In particular, it remains unclear how distillation from LLM rankers compares to distillation from strong cross-encoder teachers, or to purely supervised objectives. It is also unclear how much newer backbones (RoBERTa, ELEC...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3799682.3840914" target="_blank" rel="noopener">https://doi.org/10.1145/3799682.3840914</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3799682.3840914" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex
