Differences

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

--- nlp:prompting [2025/10/08 08:38] – [Chained or Tool-based Prompting] jmflanig
+++ nlp:prompting [2026/08/16 21:45] (current) – [Few-shot aka In-Context Learning] jmflanig
@@ Line 31: / Line 31: @@
   * [[https://arxiv.org/pdf/2005.14165.pdf|Brown et al 2021 - Language Models are Few-Shot Learners]] GPT-3
   * [[https://arxiv.org/pdf/2012.15723.pdf|Gao et al 2021 - Making Pre-trained Language Models Better Few-shot Learners]]
+  * [[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?
 ==== Many-Shot In-Context Learning ====
@@ Line 78: / Line 80: @@
   * [[https://arxiv.org/pdf/2210.01240.pdf|Saparov & He 2022 - Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought]]
   * [[https://arxiv.org/pdf/2210.03629.pdf|Yao et al 2022 - ReAct: Synergizing Reasoning and Acting in Language Models]] - The basis of LangChain
+  * **[[https://arxiv.org/pdf/2211.12588|Chen et al 2022 - Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks]]**
   * [[https://arxiv.org/pdf/2305.04091.pdf|Wang et 2023 - Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models]]
   * [[https://arxiv.org/pdf/2305.14992|Hao et al 2023 - Reasoning with Language Model is Planning with World Model]]