A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
Introduces retrieval-augmented generation (RAG), combining pre-trained parametric and non-parametric memory for knowledge-intensive NLP tasks.
Unknown
EchoRAG enhances compact LLMs with Graph-RAG and in-context learning to match or exceed larger models like 7B on knowledge-intensive tasks.
Unknown
RankRAG unifies context ranking with retrieval-augmented generation in LLMs by jointly fine-tuning a single model for both retrieval and answer generation, improving performance on knowledge-intensive tasks.
Unknown
Introduces KARD, a knowledge-augmented reasoning distillation method that enhances small language models' performance on knowledge-intensive tasks.
Jinhyuk Lee, Anthony Chen, Zhuyun Dai, et al.
This paper investigates whether long-context language models can replace traditional tools like retrieval systems and databases for knowledge-intensive tasks.