Research
===
###### tags: `Research`
Research topic
---
- [Milestone](/hPm24codTfiOc6s6y9c5fw)
Overview
---
- [Pre-Trained Models: Past, Present and Future](/3wua-WymSE6PxCdgnd8Zxw)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](/TxTRYPctSjG9aGhmIsWogQ)
- [LLaMA: Open and Efficient Foundation Language Models](/dKz1-PhMRqS2Dt3h5fy6TA)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](/vlzD2IMyS5qUsTmGa3uDQQ)
- [A Survey on Retrieval-Augmented Text Generation](/OgpOgiRlRRKQ089IduQHMw)
- [Challenges and Applications of Large Language Models](/TuCr0w_RSWiVDfcxri0K-w)
- [A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions](/9IY8N6SFRNS0bYFBwJX8bg)
- [Towards Empathetic Open-domain Conversation Models: a New Benchmark and Dataset](/wrLQNfG1RyuRQF5GA-GN2w)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](/mTKYCkM8T_-RwyCsdqGmvg)
Related work
---
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](/MpFO6n1nQ9SQW5ciZAdYPA)
- [It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](/vBaAoJ85TryLe7tVkWlvUA)
- [RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning](/uVh_GEblRISATTsBO8i_kA)
- [Parameter-efficient learned GPT](/benG-nTmSTC4uuks1FIBuw)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](/h1DoalSWRwaSYFZJws2vYw)
- [REALM: Retrieval-Augmented Language Model Pre-Training](/IIH2VfD9TTmjoFezl5h-_w)
- [Adaptive Semiparametric Language Models](/hwZRrrenRU-BLio0I062hw)
- [SalesBot: Transitioning from Chit-Chat to Task-Oriented Dialogues](/5EGGKlzBSQa0N1Nq8hbE8g)
- [Semi-Supervised Classification with Graph Convolutional Networks](/F8FiVuPtSte6akAle4n9qg)
- [Graph Attention Networks](/HDZMsB-uQgaottY3UmC6pw)
- [GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval](/YyR4wT8MQzikS1WoAXrHqw)
- [Empathetic Dialogue Generation via Knowledge Enhancing and Emotion Dependency Modeling](/26htfW-gQAegLv4V00W4PA)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](/d7ucm80wQZStQNHILz2Bvw)
- [Augmenting Neural Response Generation with Context-Aware Topical Attention](/-BxMfHZ2SBSCLt2cgMCnFw)
Related work from other members
---
- [GPT-Critic: Offline Reinforcement Learning for End-to-End Task-Oriented Dialogue Systems](/WkOBKBRvRMS_zeSF2xd8gA)
- [BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models](/JJqPV2MITcOJe_-Og2rWjg)
- [Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning](/iWnfGW6ISW6xXcyq-q8Epw)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](/jXjEQRMWRSmRV_i0GXlO4Q)
- [LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning](https://hackmd.io/@bobbiaditya/ryxUEJNKn)
LLaMA background knowledge
---
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](/OMO1tbZDSOGmgQUUeuUR3g)
- [Training Compute-Optimal Large Language Models](/0msrrwJ6QmuiaDyFtF_cPQ)
{"metaMigratedAt":"2023-06-17T19:47:47.735Z","metaMigratedFrom":"Content","title":"Research","breaks":true,"description":"Milestone","contributors":"[{\"id\":\"8008890c-8864-4761-8a67-cd9ab7a27e6d\",\"add\":3729,\"del\":641},{\"id\":\"90f849d6-338f-486f-ae7f-d98ea98f0fda\",\"add\":133,\"del\":115}]"}