[論文介紹] RAFT: Adapting Language Model to Domain Specific RAG 透過 Irrelevant Document 來訓練 RAG-LLM Oct 31.15 min read.論文介紹
[論文介紹] REPLUG: Retrieval-Augmented Black-Box Language Models RAG on Block-Box LLM,針對 Inference 與 Training 的簡單優化 Oct 31.13 min read.論文介紹
[論文介紹] Better & Faster Large Language Models via Multi-token Prediction 誰說 LLM 一定要一次預測一個 Token,預測多個不行嗎? Jul 18.8 min read.論文介紹
[論文介紹] Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning 只訓練不到 1% 的參數,就能夠讓 LLM 變成 Multimodal LLM Jul 8.8 min read.論文介紹
[論文介紹] ChatEval: Towards Better LLM-Based Evaluators Through Multi-Agent Debate LLM Agent 是什麼?Agent 之間如何進行 Debate 來完成任務? Jun 23.15 min read.論文介紹
[論文介紹] Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM 來自 Meta FAIR 的 BTX:更有效率的訓練 LLM 精通各項領域 Apr 24.15 min read.論文介紹
2022 AACL Tutorial: Recent Advances in Pre-trained Language Models 近幾年 Pre-trained Language Model 的發展 Jul 1.15 min read.深度學習核心觀念