Unlimiformer
First page

Paper summary
Long-range Transformers with unlimited length input via external datastores.
Ask this paper
01
External datastore: Augments pre-trained encoder-decoder Transformers with a kNN datastore to support arbitrary-length input.
02
Training-free: No additional training required - works with existing pretrained Transformers.
03
Long-document tasks: Demonstrates usefulness in long-document summarization where context spans many thousands of tokens.
04
RAG-enhancer: Could improve the performance of retrieval-enhanced LLMs by providing unlimited lookback over long conversations or documents.