RAG系列论文

大模型幻觉综述
Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models
链接

大模型的涌现能力
Emergent Abilities of Large Language Models

预训练模型

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
链接

T5:
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
链接

Roberta：
RoBERTa: A Robustly Optimized BERT Pretraining Approach
链接

检索增强模型：

提出Atlas ：预训练检索增强模型
Few-shot Learning with Retrieval Augmented Language Models
链接

根据输入问题的不同，挑选合适的提示词
Learning To Retrieve Prompts for In-Context Learning
链接

RAG：

Meta 2020 RAG
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
链接
阿里RAG新框架R4：增强检索器-重排序-响应器，5个知识密集任务上都超过Self-RAG
R4: Reinforced Retriever-Reorder-Responder for Retrieval-Augmented Large Language Models
链接

融合检索模型和外部wiki百科数据进行回答
AI-based Question Answering Assistance for Analyzing Natural-language Requirements
链接

检索增强模型查询重写
Query Rewriting for Retrieval-Augmented Large Language Models
链接

重排序
LLM-RankFusion: Mitigating Intrinsic Inconsistencyin LLM-based Ranking
链接