Not all layers are equally as important: Every Layer Counts BERT
Open accessAbstract
This paper introduces a novel modification of the transformer architecture, tailored for the data-efficient pretraining of language models.This aspect is evaluated by participating in the BabyLM challenge, where our solution won both the STRICT and STRICT-SMALL tracks.Our approach allows each transformer layer to select which outputs of previous layers to process.The empirical results verify the potential of this simple modification and show that not all layers are equally as important.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The best-performing models overall use the LTG-BERT architecture.
“The best-performing models overall (Charpentier and Samuel, 2023) use the LTG-BERT architecture (Samuel et al., 2023)”
From Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora (2023) · cites this paper as Charpentier and Samuel, 2023
The winner of the Strict track is ELC-BERT submitted by Charpentier and Samuel (2023).
“The winner of the Strict track is ELC-BERT submitted by Charpentier and Samuel (2023).”
From Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora (2023) · cites this paper as Charpentier and Samuel (2023)
The winning submission made architectural modifications: Charpentier and Samuel (2023) made slight improvements to LTG-BERT by taking a weighted sum over the outputs of all previous layers.
“The winning submission made architectural modifications: Charpentier and Samuel (2023) made slight improvements to LTG-BERT (see §7.2 for more on this architecture) by taking a weighted sum over the outputs of all previous layers.”
From Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora (2023) · cites this paper as Charpentier and Samuel (2023)
The winner of the Strict-Small track is ELC-BERT.
“The winner of the Strict-Small track is, again, ELC-BERT (Charpentier and Samuel, 2023).”
From Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora (2023) · cites this paper as Charpentier and Samuel, 2023
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
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 48,293 · see citing works
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · see citing works
The State and Fate of Linguistic Diversity and Inclusion in the NLP World
Joshi, P., Santy, S., Budhiraja, A., Bali, K., & Choudhury, M. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.560 · Cited by 766 · see citing works
The Computational Limits of Deep Learning
Thompson, N. C., Greenewald, K., Lee, K., & Manso, G. F. (2020) · arXiv · doi:10.48550/arxiv.2007.05558 · Cited by 538 · see citing works
Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
Warstadt, A., Mueller, A., Choshen, L., Wilcox, E., Zhuang, C., Ciro, J., Mosquera, R., Paranjabe, B., Williams, A., Linzen, T., et al. (2023) · Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning · doi:10.18653/v1/2023.conll-babylm.1 · Cited by 74 · see citing works
Trained on 100 million words and still in shape: BERT meets British National Corpus
Samuel, D., Kutuzov, A., Øvrelid, L., & Velldal, E. (2023) · Findings of the Association for Computational Linguistics: EACL 2023 · doi:10.18653/v1/2023.findings-eacl.146 · Cited by 14 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 35
- Ahmed Abdelali, Francisco Guzman, Hassan Sajjad, and Stephan Vogel. 2014. The AMARA corpus: Building parallel language resources for the educa- tional domain. In Proceedings of the Ninth Inter- national Conference on Language Resources and Evaluation (LREC'14), Reykjavik, Iceland. European Language Resources Association (ELRA).
- Thomas Bachlechner, Bodhisattwa Prasad Majumder, Henry Mao, Gary Cottrell, and Julian McAuley. 2021. Rezero is all you need: Fast convergence at large depth. In Uncertainty in Artificial Intelligence, pages 1352-1361. PMLR.
- Roy Bar-Haim, Ido Dagan, Bill Dolan, Lisa Ferro, and Danilo Giampiccolo. 2006. The second pascal recog- nising textual entailment challenge. Proceedings of the Second PASCAL Challenges Workshop on Recog- nising Textual Entailment.
- Luisa Bentivogli, Ido Dagan, Hoa Trang Dang, Danilo Giampiccolo, and Bernardo Magnini. 2009. The fifth pascal recognizing textual entailment challenge. In In Proc Text Analysis Conference (TAC'09.
- Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Ma- teusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Ad- vances in Neural Information Processing Systems, volume 33, pages 1877-1901.
- Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, and Kristina Toutanova. 2019. BoolQ: Exploring the surprising difficulty of natural yes/no questions. In Proceedings of the 2019 Conference of the North American Chap- ter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2924-2936, Minneapolis, Min- nesota. Association for Computational Linguistics. · DOI
- Ido Dagan, Oren Glickman, and Bernardo Magnini. 2006. The pascal recognising textual entailment chal- lenge. In Machine Learning Challenges. Evaluating Predictive Uncertainty, Visual Object Classification, and Recognising Tectual Entailment, pages 177-190, Berlin, Heidelberg. Springer Berlin Heidelberg.
- Eustasio Del Barrio, Juan A Cuesta-Albertos, and Car- los Matrán. 2018. An optimal transportation ap- proach for assessing almost stochastic order. In The Mathematics of the Uncertain, pages 33-44. Springer.
- William B. Dolan and Chris Brockett. 2005. Automati- cally constructing a corpus of sentential paraphrases. In Proceedings of the Third International Workshop on Paraphrasing (IWP2005).
- Rotem Dror, Segev Shlomov, and Roi Reichart. 2019. Deep dominance -how to properly compare deep neural models. In Proceedings of the 57th Annual Meeting of the Association for Computational Lin- guistics, pages 2773-2785, Florence, Italy. Associa- tion for Computational Linguistics. · DOI
- Martin Gerlach and Francesc Font-Clos. 2018. A stan- dardized Project Gutenberg corpus for statistical anal- ysis of natural language and quantitative linguistics. Computing Research Repository, arXiv:1812.08092. · DOI
- Danilo Giampiccolo, Bernardo Magnini, Ido Dagan, and Bill Dolan. 2007. The third PASCAL recognizing textual entailment challenge. In Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, pages 1-9, Prague. Association for Computational Linguistics.
- Jeremy Howard and Sebastian Ruder. 2018. Universal language model fine-tuning for text classification. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 328-339, Melbourne, Australia. Association for Computational Linguistics. · DOI · Paper page
- Ganesh Jawahar, Benoît Sagot, and Djamé Seddah. 2019. What does BERT learn about the structure of language? In Proceedings of the 57th Annual Meet- ing of the Association for Computational Linguistics, pages 3651-3657, Florence, Italy. Association for Computational Linguistics. · DOI
- Daniel Khashabi, Snigdha Chaturvedi, Michael Roth, Shyam Upadhyay, and Dan Roth. 2018. Looking beyond the surface: A challenge set for reading com- prehension over multiple sentences. In Proceedings of the 2018 Conference of the North American Chap- ter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Pa- pers), pages 252-262, New Orleans, Louisiana. As- sociation for Computational Linguistics. · DOI
- Dan Kondratyuk and Milan Straka. 2019. 75 languages, 1 model: Parsing Universal Dependencies univer- sally. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natu- ral Language Processing (EMNLP-IJCNLP), pages 2779-2795, Hong Kong, China. Association for Com- putational Linguistics. · DOI
- Hector J. Levesque, Ernest Davis, and Leora Morgen- stern. 2012. The winograd schema challenge. In Proceedings of the Thirteenth International Confer- ence on Principles of Knowledge Representation and Reasoning, KR'12, page 552-561. AAAI Press.
- Pierre Lison and Jörg Tiedemann. 2016. OpenSub- titles2016: Extracting large parallel corpora from movie and TV subtitles. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 923-929, Portorož, Slovenia. European Language Resources Association (ELRA).
- Brian MacWhinney. 2000. The CHILDES project: The database, volume 2. Psychology Press.
- B.W. Matthews. 1975. Comparison of the predicted and observed secondary structure of t4 phage lysozyme. Biochimica et Biophysica Acta (BBA) -Protein Struc- ture, 405(2):442-451. · DOI · Paper page
- Jingcheng Niu, Wenjie Lu, and Gerald Penn. 2022. Does BERT rediscover a classical NLP pipeline? In Proceedings of the 29th International Conference on Computational Linguistics, pages 3143-3153, Gyeongju, Republic of Korea. International Com- mittee on Computational Linguistics.
- Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natu- ral Language Processing, pages 2383-2392, Austin, Texas. Association for Computational Linguistics. · DOI · Paper page
- Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empiri- cal Methods in Natural Language Processing, pages 1631-1642, Seattle, Washington, USA. Association for Computational Linguistics.
- Rupesh K Srivastava, Klaus Greff, and Jürgen Schmid- huber. 2015. Training very deep networks. In Ad- vances in Neural Information Processing Systems, volume 28.
- Andreas Stolcke, Klaus Ries, Noah Coccaro, Elizabeth Shriberg, Rebecca Bates, Daniel Jurafsky, Paul Tay- lor, Rachel Martin, Marie Meteer, and Carol Van Ess-Dykema. 2000. Dialogue act modeling for au- tomatic tagging and recognition of conversational speech. Computational Linguistics, 26(3):339-371.
- Emma Strubell, Ananya Ganesh, and Andrew McCal- lum. 2019. Energy and policy considerations for deep learning in NLP. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3645-3650, Florence, Italy. Asso- ciation for Computational Linguistics. · DOI · Paper page
- Ian Tenney, Dipanjan Das, and Ellie Pavlick. 2019. BERT rediscovers the classical NLP pipeline. In Proceedings of the 57th Annual Meeting of the Asso- ciation for Computational Linguistics, pages 4593- 4601, Florence, Italy. Association for Computational Linguistics. · DOI · Paper page
- Dennis Ulmer, Christian Hardmeier, and Jes Frellsen. 2022. deep-significance: Easy and meaningful sig- nifcance testing in the age of neural networks. In ML Evaluation Standards Workshop at the Tenth Interna- tional Conference on Learning Representations.
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30.
- Alex Wang, Yada Pruksachatkun, Nikita Nangia, Aman- preet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2019. Superglue: A stickier benchmark for general-purpose language understand- ing systems. In Advances in Neural Information Processing Systems, volume 32.
- Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for nat- ural language understanding. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 353-355, Brussels, Belgium. Association for Com- putational Linguistics. · DOI · Paper page
- Alex Warstadt, Alicia Parrish, Haokun Liu, Anhad Mo- hananey, Wei Peng, Sheng-Fu Wang, and Samuel R Bowman. 2020a. Blimp: The benchmark of linguis- tic minimal pairs for english. Transactions of the Association for Computational Linguistics, 8:377- 392.
- Alex Warstadt, Amanpreet Singh, and Samuel R. Bow- man. 2019. Neural network acceptability judgments. Transactions of the Association for Computational Linguistics, 7:625-641. · DOI
- Alex Warstadt, Yian Zhang, Haau-Sing Li, Haokun Liu, and Samuel R Bowman. 2020b. Learning which features matter: Roberta acquires a preference for lin- guistic generalizations (eventually). arXiv preprint arXiv:2010.05358. · arXiv
- Adina Williams, Nikita Nangia, and Samuel Bowman. 2018. A broad-coverage challenge corpus for sen- tence understanding through inference. In Proceed- ings of the 2018 Conference of the North American Chapter of the Association for Computational Lin- guistics: Human Language Technologies, Volume 1 (Long Papers), pages 1112-1122, New Orleans, Louisiana. Association for Computational Linguis- tics. · DOI · Paper page
Cited by
Sorted by citations
Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
Warstadt, A., Mueller, A., Choshen, L., Wilcox, E., Zhuang, C., Ciro, J., Mosquera, R., Paranjabe, B., Williams, A., Linzen, T., et al. (2023) · Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning · doi:10.18653/v1/2023.conll-babylm.1 · Cited by 74 · see citing works
Bigger is not always better: The importance of human-scale language modeling for psycholinguistics
Wilcox, E. G., Hu, M. Y., Mueller, A., Warstadt, A., Choshen, L., Zhuang, C., Williams, A., Cotterell, R., & Linzen, T. (2025) · Journal of Memory and Language · doi:10.1016/j.jml.2025.104650 · Cited by 9 · see citing works
- Authors
- Georges Gabriel Charpentier, L., & Samuel, D.
- Affiliations
- University of Oslo (NO)
- Venue
- Proceedings of the BabyLM Challenge at the 27th Conference on Computational Natural Language Learning
- Published
- 2023
- Pages
- 210-224
- OpenAlex
- W4389524424
- Cited by
- 9
- References
- 7
- Citations by year
- 2026: 2 · 2025: 4 · 2024: 2 · 2023: 1
- FWCI
- 1.59
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- dx.doi.org
- Licence
- cc-by
- Locations
- BabyLM Challenge (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- Univerzita Karlova v Praze
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- layer selection, language model pretraining, layer importance
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
