RETRO-LI: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift Generalization


Loading...

Date

2024

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

The retrieval augmented generation (RAG) system such as RETRO has been shown to improve language modeling capabilities and reduce toxicity and hallucinations by retrieving from a database of non-parametric memory containing trillions of entries. We introduce RETRO-LI that shows retrieval can also help using a small scale database, but it demands more accurate and better neighbors when searching in a smaller hence sparser nonparametric memory. This can be met by using a proper semantic similarity search. We further propose adding a regularization to the non-parametric memory for the first time: it significantly reduces perplexity when the neighbor search operations are noisy during inference, and it improves generalization when a domain shift occurs. We also show that the RETRO-LI’s non-parametric memory can potentially be implemented on analog in-memory computing hardware, exhibiting O(1) search time while causing noise in retrieving neighbors, with minimal (<1%) performance loss. Our code is available at: https://github.com/IBM/Retrieval-Enhanced-Transformer-Little

Publication status

published

Book title

ECAI 2024

Volume

392

Pages / Article No.

2974 - 2982

Publisher

IOS Press

Event

27th European Conference on Artificial Intelligence (ECAI 2024)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

Notes

Funding

Related publications and datasets