Differences

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

--- nlp:retrieval-augmented_methods [2025/05/13 19:39] – [Papers] jmflanig
+++ nlp:retrieval-augmented_methods [2026/08/16 21:40] (current) – [Papers] jmflanig
@@ Line 5: / Line 5: @@
 ===== Papers =====
-  * **[[https://arxiv.org/pdf/2005.11401.pdf|Lewis et al 2020 - Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks]]**
+  * **[[https://arxiv.org/pdf/2005.11401.pdf|Piktus et al 2020 - Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks]]** (Mike Lewis)
   * [[https://arxiv.org/pdf/2101.06804.pdf|Liu et al 2021 - What Makes Good In-Context Examples for GPT-3?]] Cited by [[https://arxiv.org/pdf/2112.08633.pdf|Rubin 2021]]
   * [[https://arxiv.org/pdf/2112.08633.pdf|Rubin et al 2021 - Learning To Retrieve Prompts for In-Context Learning]] Is this the first retrieval-based in-context learning paper?
@@ 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/2401.14021.pdf|Zhang et al 2024 - Accelerating Retrieval-Augmented Language Model Serving with Speculation]]
+  * **[[https://arxiv.org/pdf/2410.07590|Lu et al 2025 - TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text]]**
   * [[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]]