From 71f54d49ce4da246b794f6df48435420527ac4b7 Mon Sep 17 00:00:00 2001
From: mac <18800151059@163.com>
Date: Thu, 23 Feb 2023 00:22:32 +0800
Subject: [PATCH] add instruction tuning

---
 README.md                                     |  3 +-
 paper_list/instruction-tuning.md              | 30 +++++++++++++++++++
 .../{prompt_tuning.md => prompt_learning.md}  |  3 +-
 3 files changed, 34 insertions(+), 2 deletions(-)
 create mode 100644 paper_list/instruction-tuning.md
 rename paper_list/{prompt_tuning.md => prompt_learning.md} (90%)

diff --git a/README.md b/README.md
index b237c48..dee3b2b 100644
--- a/README.md
+++ b/README.md
@@ -64,7 +64,8 @@ If you're interested in the field of LLM, you may find the above list of milesto
 - [Chain-of-Thought](paper_list/chain_of_thougt.md)
 - [In-Context-Learning](paper_list/in_context_learning.md)
 - [RLHF](paper_list/RLHF.md)
-- [Prompt-Tuning](paper_list/prompt_tuning.md)
+- [Prompt-Learning](paper_list/prompt_learning.md)
+- [Instruction-Tuning](paper_list/instruction-tuning.md)
 - [MOE](paper_list/moe.md)
 - [Code-Pretraining](paper_list/code_pretraining.md)
 - [LLM-Evaluation](paper_list/protein_pretraining.md)
diff --git a/paper_list/instruction-tuning.md b/paper_list/instruction-tuning.md
new file mode 100644
index 0000000..186fcc7
--- /dev/null
+++ b/paper_list/instruction-tuning.md
@@ -0,0 +1,30 @@
+# Instruction-Tuning
+
+## Papers
+
+### 2021
+
+- **Cross-task generalization via natural language crowdsourcing instructions.** (2021-04) Swaroop Mishra et al. [paper](https://arxiv.org/abs/2104.08773)
+- **Adapting language models for zero-shot learning by meta-tuning on dataset and prompt collections** (2021-04) Ruiqi Zhong et al. [paper](https://aclanthology.org/2021.findings-emnlp.244/)
+- **Crossfit: A few-shot learning challenge for cross-task general- ization in NLP** (2021-04) QinYuan Ye et al. [paper](https://arxiv.org/abs/2104.08835)
+
+- **Finetuned language models are zero-shot learners** (2021-09) Jason Wei et al. [paper](https://openreview.net/forum?id=gEZrGCozdqR) 
+
+  > FLAN
+
+- **Multitask prompted training enables zero-shot task generalization** (2021-10) Victor Sanh et al. [paper](https://openreview.net/forum?id=9Vrb9D0WI4)
+
+- **MetaICL: Learning to learn in context** (2021-10) Sewon Min et al. [paper](https://arxiv.org/abs/2110.15943#:~:text=We%20introduce%20MetaICL%20%28Meta-training%20for%20In-Context%20Learning%29%2C%20a,learning%20on%20a%20large%20set%20of%20training%20tasks.)
+
+### 2022
+
+- **Training language models to follow instructions with human feedback.** (2022-03) Long Ouyang et al. [paper](https://arxiv.org/abs/2203.02155)
+
+- **Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks** (2022-04) Yizhong Wang et al. [paper](https://arxiv.org/abs/2204.07705)
+
+- **Scaling Instruction-Finetuned Language Models** (20220-10) Hyung Won Chung et al. [paper](https://arxiv.org/pdf/2210.11416.pdf)
+
+  > Flan-T5/PaLM
+
+## Useful Resources
+
diff --git a/paper_list/prompt_tuning.md b/paper_list/prompt_learning.md
similarity index 90%
rename from paper_list/prompt_tuning.md
rename to paper_list/prompt_learning.md
index 29d3d6f..2c0f545 100644
--- a/paper_list/prompt_tuning.md
+++ b/paper_list/prompt_learning.md
@@ -1,6 +1,7 @@
-# Prompt Tuning
+# Prompt Learning
 
 ## Papers
 - **Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing** (2021-07) Pengfei Liu et al. [paper](https://arxiv.org/abs/2107.13586)
   > A Systematic Survey
+
 ## Useful Resources