{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T05:04:53Z","timestamp":1772082293042,"version":"3.50.1"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643685489","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,16]]},"abstract":"<jats:p>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 non-parametric 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\u2019s 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 (&lt;1%) performance loss. Our code is available at: https:\/\/github.com\/IBM\/Retrieval-Enhanced-Transformer-Little<\/jats:p>","DOI":"10.3233\/faia240837","type":"book-chapter","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T13:31:20Z","timestamp":1729171880000},"source":"Crossref","is-referenced-by-count":1,"title":["RETRO-LI: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift Generalization"],"prefix":"10.3233","author":[{"given":"Gentiana","family":"Rashiti","sequence":"first","affiliation":[{"name":"IBM Research \u2013 Zurich"},{"name":"ETH Z\u00fcrich"}]},{"given":"Geethan","family":"Karunaratne","sequence":"additional","affiliation":[{"name":"IBM Research \u2013 Zurich"}]},{"given":"Mrinmaya","family":"Sachan","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich"}]},{"given":"Abu","family":"Sebastian","sequence":"additional","affiliation":[{"name":"IBM Research \u2013 Zurich"}]},{"given":"Abbas","family":"Rahimi","sequence":"additional","affiliation":[{"name":"IBM Research \u2013 Zurich"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2024"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA240837","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T13:31:20Z","timestamp":1729171880000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA240837"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"ISBN":["9781643685489"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia240837","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]}}}