BibTeX

@inProceedings{norlund-etal-2023-generalization-326357,
	title        = {On the Generalization Ability of Retrieval-Enhanced Transformers},
	abstract     = {Recent work on the Retrieval-Enhanced Transformer (RETRO) model has shown impressive results: off-loading memory from trainable weights to a retrieval database can significantly improve language modeling and match the performance of non-retrieval models that are an order of magnitude larger in size. It has been suggested that at least some of this performance gain is due to non-trivial generalization based on both model weights and retrieval. In this paper, we try to better understand the relative contributions of these two components. We find that the performance gains from retrieval to a very large extent originate from overlapping tokens between the database and the test data, suggesting less of non-trivial generalization than previously assumed. More generally, our results point to the challenges of evaluating the generalization of retrieval-augmented language models such as RETRO, as even limited token overlap may significantly decrease test-time loss. We release our code and model at https://github.com/TobiasNorlund/retro},
	booktitle    = {Findings of the Association for Computational Linguistics: EACL 2023, pages 1485–1493, Dubrovnik, Croatia},
	author       = {Norlund, Tobias and Doostmohammadi, Ehsan and Johansson, Richard and Kuhlmann, Marco},
	year         = {2023},
	publisher    = {Association for Computational Linguistics},
}