%0 Generic %1 borgeaud2021improving %A Borgeaud, Sebastian %A Mensch, Arthur %A Hoffmann, Jordan %A Cai, Trevor %A Rutherford, Eliza %A Millican, Katie %A Driessche, George van den %A Lespiau, Jean-Baptiste %A Damoc, Bogdan %A Clark, Aidan %A Casas, Diego de Las %A Guy, Aurelia %A Menick, Jacob %A Ring, Roman %A Hennigan, Tom %A Huang, Saffron %A Maggiore, Loren %A Jones, Chris %A Cassirer, Albin %A Brock, Andy %A Paganini, Michela %A Irving, Geoffrey %A Vinyals, Oriol %A Osindero, Simon %A Simonyan, Karen %A Rae, Jack W. %A Elsen, Erich %A Sifre, Laurent %D 2021 %K llm retrieval %T Improving language models by retrieving from trillions of tokens %U http://arxiv.org/abs/2112.04426 %X We enhance auto-regressive language models by conditioning on document chunks retrieved from a large corpus, based on local similarity with preceding tokens. With a $2$ trillion token database, our Retrieval-Enhanced Transformer (RETRO) obtains comparable performance to GPT-3 and Jurassic-1 on the Pile, despite using 25$\times$ fewer parameters. After fine-tuning, RETRO performance translates to downstream knowledge-intensive tasks such as question answering. RETRO combines a frozen Bert retriever, a differentiable encoder and a chunked cross-attention mechanism to predict tokens based on an order of magnitude more data than what is typically consumed during training. We typically train RETRO from scratch, yet can also rapidly RETROfit pre-trained transformers with retrieval and still achieve good performance. Our work opens up new avenues for improving language models through explicit memory at unprecedented scale.

@misc{borgeaud2021improving, abstract = {We enhance auto-regressive language models by conditioning on document chunks retrieved from a large corpus, based on local similarity with preceding tokens. With a $2$ trillion token database, our Retrieval-Enhanced Transformer (RETRO) obtains comparable performance to GPT-3 and Jurassic-1 on the Pile, despite using 25$\times$ fewer parameters. After fine-tuning, RETRO performance translates to downstream knowledge-intensive tasks such as question answering. RETRO combines a frozen Bert retriever, a differentiable encoder and a chunked cross-attention mechanism to predict tokens based on an order of magnitude more data than what is typically consumed during training. We typically train RETRO from scratch, yet can also rapidly RETROfit pre-trained transformers with retrieval and still achieve good performance. Our work opens up new avenues for improving language models through explicit memory at unprecedented scale.}, added-at = {2023-08-17T15:00:46.000+0200}, author = {Borgeaud, Sebastian and Mensch, Arthur and Hoffmann, Jordan and Cai, Trevor and Rutherford, Eliza and Millican, Katie and Driessche, George van den and Lespiau, Jean-Baptiste and Damoc, Bogdan and Clark, Aidan and Casas, Diego de Las and Guy, Aurelia and Menick, Jacob and Ring, Roman and Hennigan, Tom and Huang, Saffron and Maggiore, Loren and Jones, Chris and Cassirer, Albin and Brock, Andy and Paganini, Michela and Irving, Geoffrey and Vinyals, Oriol and Osindero, Simon and Simonyan, Karen and Rae, Jack W. and Elsen, Erich and Sifre, Laurent}, biburl = {https://www.bibsonomy.org/bibtex/2ab005037001dc6fdb460707bf397702b/lisa-ee}, description = {Improving language models by retrieving from trillions of tokens}, interhash = {4a49951e42bb8e4532abd193e6be9b3a}, intrahash = {ab005037001dc6fdb460707bf397702b}, keywords = {llm retrieval}, note = {cite arxiv:2112.04426Comment: Fix incorrect reported numbers in Table 14}, timestamp = {2023-08-17T15:00:46.000+0200}, title = {Improving language models by retrieving from trillions of tokens}, url = {http://arxiv.org/abs/2112.04426}, year = 2021 }