## Focus on Language model & Prompt learning
- 2023/02/02 Learn prompt based on [PromptPapers](https://github.com/thunlp/PromptPapers)
- 2023/02/02 [Paper] Pre-Trained Models: Past, Present and Future
- 2023/02/07 [Paper] It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners
- 2023/02/07 [Paper] Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference
- 2023/02/11 [Paper] Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
- 2023/02/11 [Demo] pet
- 2023/03/17 [Paper] RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
- 2023/08/01 [Paper] Challenges and Applications of Large Language Models

## Focus on NLP with RL methods

- 2023/04/18 [Group] Is Reinforcement Learning (Not) for Natural Language Processing
- 2023/04/27 [Group] A Mixture-of-Expert Approach to RL-based Dialogue Management

## Focus on Parameter-efficient NLG

- 2023/05/09 [NLG] Evaluating Parameter Efficient Learning for Generation
- 2023/06/27 [NLG] Parameter-efficient learned GPT
- Control Prefixes for Parameter-Efficient Text Generation
- AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning
- Parameter-Efficient Sparsity for Large Language Models Fine-Tuning
- Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning
- HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks

## Focus on LLaMA and related works

- 2023/06/28 [Paper] LLaMA: Open and Efficient Foundation Language Models
- 2023/07/01 [Paper] RoFormer: Enhanced Transformer with Rotary Position Embedding
- 2023/07/06 [Paper] Training Compute-Optimal Large Language Models
- 2023/07/07 [Paper] Self-instruct: Aligning language model with self generated instructions
- 2023/07/19 [Paper] Llama 2: Open Foundation and Fine-Tuned Chat Models
- 2023/07/25 [Group] LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

## Focus on RAG

- 2023/05/30 [Group] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- 2023/06/27 [Group] Active Retrieval Augmented Generation
- 2023/07/17 [Paper] A Survey on Retrieval-Augmented Text Generation
- 2023/08/07 [Paper] REALM: Retrieval-Augmented Language Model Pre-Training
- 2023/08/09 [Paper] Adaptive Semiparametric Language Models
- 2023/08/25 [Paper] Transformer Memory as a Differentiable Search Index
- 2023/08/29 [Group] A Neural Corpus Indexer for Document Retrieval
- 2023/09/01 [NLG] Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback

## Focus on Mult-turn prompting

- 2023/08/12 [Paper] Ask Me Anything: A simple strategy for prompting language models

## Focus on Graph Neural Network

- 2024/01/14 [Paper] Semi-Supervised Classification with Graph Convolutional Networks
- 2024/01/19 [Paper] Graph Attention Networks
- 2024/01/22 [Paper] GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval

## Focus on Empathetic Dialogue Generation

- 2024/01/25 [Paper] Empathetic Dialogue Generation via Knowledge Enhancing and Emotion Dependency Modeling
- 2024/01/25 [Paper] Towards Empathetic Open-domain Conversation Models: a New Benchmark and Dataset

## Focus on Graph

- 2024/02/05 [Paper] ConceptNet 5.5: An Open Multilingual Graph of General Knowledge

## Focus on Topic Model

- 2024/02/16 [Paper] Augmenting Neural Response Generation with Context-Aware Topical Attention

## Focus on Multi-turn Dialogue Response

- 2024/05/27 [Paper] Advances in Multi-turn Dialogue Comprehension: A Survey