NLP Wiki

User Tools

Site Tools

Trace: • distributed_training • learning_rate • state-space_models • patent_domain_nlp • writing_assistants • zero-shot_learning • gpu_deep_learning • miscellaneous_neural_networks • morphological_analysis • distribution_shift
nlp:retrieval-augmented_methods

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
nlp:retrieval-augmented_methods [2025/04/30 19:53] – jmflanignlp:retrieval-augmented_methods [2025/05/13 19:39] (current) – [Papers] jmflanig
Line 14: Line 14:
   * **[[https://arxiv.org/pdf/2310.01352.pdf|Lin et al 2023 - RA-DIT: Retrieval-Augmented Dual Instruction Tuning]]** Fine-tunes a language model so it's better for retrieval augmented use.  Best performance occurs after a small number of fine-tuning steps (<500 steps!).   * **[[https://arxiv.org/pdf/2310.01352.pdf|Lin et al 2023 - RA-DIT: Retrieval-Augmented Dual Instruction Tuning]]** Fine-tunes a language model so it's better for retrieval augmented use.  Best performance occurs after a small number of fine-tuning steps (<500 steps!).
   * [[https://arxiv.org/pdf/2401.14021.pdf|Zhang et al 2024 - Accelerating Retrieval-Augmented Language Model Serving with Speculation]]   * [[https://arxiv.org/pdf/2401.14021.pdf|Zhang et al 2024 - Accelerating Retrieval-Augmented Language Model Serving with Speculation]]
 +  * [[https://arxiv.org/pdf/2502.16101|Zheng et al 2025 - Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals]]
  
 ==== During Pre-Training ==== ==== During Pre-Training ====
nlp/retrieval-augmented_methods.1746042839.txt.gz · Last modified: 2025/04/30 19:53 by jmflanig
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki