Adaptive Semiparametric Language Models
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
We present a language model that combines a large parametric neural network (i.e., a transformer) with a non-parametric episodic memory component in an integrated architecture. Our model uses extended short-term context by caching local hidden states—similar to transformer-XL—and global long-term memory by retrieving a set of nearest neighbor tokens at each timestep. We design a gating function to adaptively combine multiple information sources to make a prediction. This mechanism allows the model to use either local context, short-term memory, or long-term memory (or any combination of them) on an ad hoc basis depending on the context. Experiments on word-based and character-based language modeling datasets demonstrate the efficacy of our proposed method compared to strong baselines.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Transformer-XL: Attentive language models beyond a fixed-length context
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., & Salakhutdinov, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1285 · Cited by 3,169 · cited 5×
“The top rows contain results taken from other papers: (a) transformerXL (Dai et al., 2019), (b) adaptive input embeddings (Baevski and Auli, 2019), (c) compressive transformer (Rae et al.”
BackgroundMethodInfluentialLongformer: The Long-Document Transformer
Beltagy, I., Peters, M. E., & Cohan, A. (2020) · arXiv · doi:10.48550/arxiv.2004.05150 · Cited by 2,281
How many memory systems are there?
Tulving, E. (1985) · American Psychologist · doi:10.1037/0003-066x.40.4.385 · Cited by 1,909
Language Models as Knowledge Bases?
Petroni, F., Rocktäschel, T., Riedel, S., Lewis, P., Bakhtin, A., Wu, Y., & Miller, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1250 · Cited by 1,834
Reformer: The Efficient Transformer
Kitaev, N., Kaiser, Ł., & Levskaya, A. (2020) · arXiv · doi:10.48550/arxiv.2001.04451 · Cited by 1,435 · cited 1×
“, 2020), and reformer (Kitaev et al., 2020)—can be seen as models of working memory.”
BackgroundRethinking Attention with Performers
Choromanski, K., Likhosherstov, V., Dohan, D., Song, X., Gane, A., Sarlos, T., Hawkins, P., Davis, J., Mohiuddin, A., Kaiser, L., et al. (2020) · arXiv · doi:10.48550/arxiv.2009.14794 · Cited by 695
Generating Sentences by Editing Prototypes
Guu, K., Hashimoto, T. B., Oren, Y., & Liang, P. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00030 · Cited by 300
Generalization through Memorization: Nearest Neighbor Language Models
Khandelwal, U., Levy, O., Jurafsky, D., Zettlemoyer, L., & Lewis, M. (2019) · arXiv · doi:10.48550/arxiv.1911.00172 · Cited by 285
Cited by
A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
Fan, W., Ding, Y., Ning, L., Wang, S., Li, H., Yin, D., Chua, T.-S., & Li, Q. (2024) · Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3637528.3671470 · Cited by 827
“To tackle this limitation, Yogatama et al. [145] propose to add an extra gating network to post-process the retrieved data and achieve comparatively better performance.”
Retrieval Augmentation Reduces Hallucination in Conversation
Shuster, K., Poff, S., Chen, M., Kiela, D., & Weston, J. (2021) · Findings of the Association for Computational Linguistics: EMNLP 2021 · doi:10.18653/v1/2021.findings-emnlp.320 · Cited by 575
Stade, E. C., Stirman, S. W., Ungar, L. H., Boland, C. L., Schwartz, H. A., Yaden, D. B., Sedoc, J., DeRubeis, R. J., Willer, R., & Eichstaedt, J. C. (2024) · npj Mental Health Research · doi:10.1038/s44184-024-00056-z · Cited by 391
“Inaddition,itisalreadypossibletoaugmentthememoryofLLMswith “ vector databases, ” which would have the added bene fi t of retaining inspectable learnings and summaries across clinical encounters 72 .”
BackgroundData augmentation approaches in natural language processing: A survey
Li, B., Hou, Y., & Che, W. (2022) · AI Open · doi:10.1016/j.aiopen.2022.03.001 · Cited by 350
Atlas: Few-shot Learning with Retrieval Augmented Language Models
Izacard, G., Lewis, P., Lomeli, M., Hosseini, L., Petroni, F., Schick, T., Dwivedi-Yu, J., Joulin, A., Riedel, S., & Grave, E. (2022) · arXiv · doi:10.48550/arxiv.2208.03299 · Cited by 213
Dense Text Retrieval Based on Pretrained Language Models: A Survey
Zhao, W. X., Liu, J., Ren, R., & Wen, J.-R. (2024) · ACM Transactions on Information Systems · doi:10.1145/3637870 · Cited by 211
“[315] incorporate a gating mechanism to replace the fixed interpolation parameter in kNN-LM, which adaptively combines short-term memory with long-term memory (i.”
BackgroundInternet-Augmented Dialogue Generation
Komeili, M., Shuster, K., & Weston, J. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.579 · Cited by 192
Mind the Gap: Assessing Temporal Generalization in Neural Language Models
Lazaridou, A., Kuncoro, A., Gribovskaya, E., Agrawal, D., Liska, A., Terzi, T., Gimenez, M., d'Autume, C. D. M., Kocisky, T., Ruder, S., et al. (2021) · arXiv · doi:10.48550/arxiv.2102.01951 · Cited by 90
“Another promising direction is to disentangle the acquisition of up-to-date knowledge (for instance by retrieving external information) from the language learning itself, as recently proposed by Guu et al. (2020) and Yogatama et al. (2021), among others.”
BackgroundSelf-citationRetrieval-based Language Models and Applications
Asai, A., Min, S., Zhong, Z., & Chen, D. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts) · doi:10.18653/v1/2023.acl-tutorials.6 · Cited by 81
“…are latent and integrated into the intermediate layers of Transformers (de Jong et al., 2022; Févry et al., 2020; Borgeaud et al., 2022), or 3) distribution of tokens from the retrieved components and the LMs are interpolated (Khandelwal et al., 2020; Zhong et al., 2022; Yogatama et al., 2021).”
BackgroundTraining language models with memory augmentation
Zhong, Z., Lei, T., & Chen, D. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.382 · Cited by 60
Efficient Nearest Neighbor Language Models
He, J., Neubig, G., & Berg-Kirkpatrick, T. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.461 · Cited by 97
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
Zhang, Y., Sun, R., Chen, Y., Pfister, T., Zhang, R., & Arik, S. Ö. (2024) · arXiv · doi:10.48550/arxiv.2406.02818 · Cited by 47
“Previous studies have augmented LLMs during pretraining [26, 72], finetuning [34], inference [87], or directly integrating [28, 61].”
Relational memory-augmented language models
Liu, Q., Yogatama, D., & Blunsom, P. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00476 · Cited by 23
Self-citationShall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
Wang, B., Ping, W., Xu, P., McAfee, L., Liu, Z., Shoeybi, M., Dong, Y., Kuchaiev, O., Li, B., Xiao, C., et al. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.482 · Cited by 21
∞-former: Infinite Memory Transformer-former: Infinite Memory Transformer
Martins, P. H., Marinho, Z., & Martins, A. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.375 · Cited by 15
Metadata
- Authors
- Yogatama, D., de Masson d’Autume, C., & Kong, L.
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press
- Published
- 2021
- Volume
- 9
- Pages
- 362-373
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W3157700644
- Cited by
- 56
- References
- 15
- FWCI
- 4.50
- Type
- journal article
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.