update

paper_list/acceleration.md

@@ -1,6 +1,10 @@
 # Acceleration
-Acceleration for LLM training and inference.
+> Hardware and software acceleration for LLM training and inference
 
 ## Papers
-- **High-throughput Generative Inference of Large Language Models with a single GPU** (2023-02) Ying Sheng et al. [Paper](https://github.com/FMInference/FlexGen/blob/main/docs/paper.pdf) | [Github](https://github.com/FMInference/FlexGen)
+
+### 2023
+
+- (2023-02)  **High-throughput Generative Inference of Large Language Models with a single GPU** Ying Sheng et al. [Paper](https://github.com/FMInference/FlexGen/blob/main/docs/paper.pdf) | [Github](https://github.com/FMInference/FlexGen)
+
 ## Useful Resources

paper_list/application.md

@@ -0,0 +1,16 @@
+# Application
+
+> Augment LLM in different aspects including faithfulness, expressiveness, domain-specific knowledge etc.
+
+## Papers
+
+### 2022
+
+- (2022-10) **Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing** [paper](https://arxiv.org/abs/2210.13669)
+
+### 2023
+
+- (2023-03) **Mixture of Soft Prompts for Controllable Data Generation** [paper](https://arxiv.org/pdf/2303.01580.pdf)
+
+## Useful Resources
+

paper_list/augmentation.md

@@ -0,0 +1,11 @@
+# Augmentation
+
+## Papers
+
+### 2023
+
+- (2023-01) **REPLUG: Retrieval-Augmented Black-Box Language Models** [paper](https://arxiv.org/abs/2301.12652)
+- (2023-02) **Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback** [paper](https://arxiv.org/abs/2302.12813)
+- (2023-02) **Augmented Language Models: a Survey** [paper](https://arxiv.org/abs/2302.07842)
+
+## Useful Resources

paper_list/chain_of_thougt.md

@@ -4,7 +4,9 @@
 
 ## Papers
 
-- **Chain of Thought Prompting Elicits Reasoning in Large Language Models.** (2021-01), Jason Wei et al. [[pdf]](https://arxiv.org/abs/2201.11903)
+### 2021
+
+- (2021-01) **Chain of Thought Prompting Elicits Reasoning in Large Language Models.**  [paper](https://arxiv.org/abs/2201.11903)
 
   > The first paper propose the idea of chain-of-thought
 

paper_list/instruction-tuning.md

@@ -4,25 +4,25 @@
 
 ### 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)
+- (2021-04) **Cross-task generalization via natural language crowdsourcing instructions.** [paper](https://arxiv.org/abs/2104.08773)
+- (2021-04) **Adapting language models for zero-shot learning by meta-tuning on dataset and prompt collections** [paper](https://aclanthology.org/2021.findings-emnlp.244/)
+- (2021-04) **Crossfit: A few-shot learning challenge for cross-task general- ization in NLP** [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) 
+- (2021-09) **Finetuned language models are zero-shot learners** [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)
+- (2021-10) **Multitask prompted training enables zero-shot task generalization**  [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.)
+- (2021-10) **MetaICL: Learning to learn in context**  [paper](https://arxiv.org/abs/2110.15943)
 
 ### 2022
 
-- **Training language models to follow instructions with human feedback.** (2022-03) Long Ouyang et al. [paper](https://arxiv.org/abs/2203.02155)
+- (2022-03) **Training language models to follow instructions with human feedback.**  [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)
+- (2022-04) **Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks** [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)
+- (20220-10) **Scaling Instruction-Finetuned Language Models**  [paper](https://arxiv.org/pdf/2210.11416.pdf)
 
   > Flan-T5/PaLM
 

paper_list/prompt_learning.md

@@ -1,8 +1,15 @@
 # Prompt Learning
 
 ## Papers
-- **Making Pre-trained Language Models Better Few-shot Learners** (202-12) Tianyu Gao et al. [paper](https://arxiv.org/pdf/2012.15723.pdf)
-- **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)
+
+### 2020
+
+- (2020-12) **Making Pre-trained Language Models Better Few-shot Learners**  [paper](https://arxiv.org/pdf/2012.15723.pdf)
+
+### 2021
+
+- (2021-07)  **Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing** [paper](https://arxiv.org/abs/2107.13586)
+
   > A Systematic Survey
 
 ## Useful Resources

paper_list/protein_pretraining.md

@@ -2,4 +2,34 @@
 
 ## Papers
 
-- **How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks.** (2023-03), Xuanting Chen, Junjie Ye et al. [[pdf]](https://arxiv.org/abs/2303.00293)
+### 2022
+
+- (2022-09) **News Summarization and Evaluation in the Era of GPT-3** [paper](https://arxiv.org/abs/2209.12356)
+
+### 2023
+
+- (2023-01) **How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection** [paper](https://arxiv.org/abs/2301.07597) | [project](https://github.com/Hello-SimpleAI/chatgpt-comparison-detection)
+
+- (2023-01) **Is ChatGPT A Good Translator? A Preliminary Study** [paper](https://arxiv.org/abs/2301.08745v2) | [code](https://github.com/wxjiao/Is-ChatGPT-A-Good-Translator)
+
+  >:exclamation: They only randomly select 50 sentences for evaluation, since there is no available API.
+
+- (2023-01) **Benchmarking Large Language Models for News Summarization** [paper](https://arxiv.org/abs/2301.13848)
+
+- (2023-02) **Is ChatGPT a General-Purpose Natural Language Processing Task Solver?** [paper](https://arxiv.org/abs/2302.06476)
+
+  >:exclamation: No large dataset evaluation, no few-shot in-context learning evaluation, due to lack of API.
+
+- (2023-02) **ChatGPT: Jack of all trades, master of none** [paper](https://arxiv.org/abs/2302.10724)
+
+- (2023-02) **Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT** [paper](https://arxiv.org/abs/2302.10198)
+
+- (2023-02) **On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective** [paper](https://arxiv.org/abs/2302.12095)
+
+- (2023-02) **Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization** [paper](https://arxiv.org/abs/2302.08081)
+
+- (2023-03) **How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks.** [paper](https://arxiv.org/abs/2303.00293)
+- (2023-02) **ChatGPT: potential, prospects, and limitations** [paper](https://doi.org/10.1631/FITEE.2300089)
+
+## Useful Resources
+