{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/not-all-layers-are-equally-as-important-every","title":"Not all layers are equally as important: Every Layer Counts BERT","arxiv_id":"2311.02265","date":"2023-11-03","proceeding":null,"authors":["Lucas Georges Gabriel Charpentier","David Samuel"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2311.02265v2","url_pdf":"https://arxiv.org/pdf/2311.02265v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"linguistic-acceptability","task_name":"Linguistic Acceptability"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"LTG-BERT-base 98M","rank_in_archive_order":6,"of":43,"metrics":{"Accuracy":"82.7"},"uses_additional_data":false},{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"ELC-BERT-base 98M","rank_in_archive_order":7,"of":43,"metrics":{"Accuracy":"82.6"},"uses_additional_data":false},{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"LTG-BERT-small 24M","rank_in_archive_order":10,"of":43,"metrics":{"Accuracy":"77.6"},"uses_additional_data":false},{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"ELC-BERT-small 24M","rank_in_archive_order":11,"of":43,"metrics":{"Accuracy":"76.1"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-multinli","task":"Natural Language Inference","dataset":"MultiNLI","model":"ELC-BERT-base 98M (zero init)","rank_in_archive_order":32,"of":67,"metrics":{"Matched":"84.4","Mismatched":"84.5"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-multinli","task":"Natural Language Inference","dataset":"MultiNLI","model":"LTG-BERT-base 98M","rank_in_archive_order":36,"of":67,"metrics":{"Matched":"83","Mismatched":"83.4"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-multinli","task":"Natural Language Inference","dataset":"MultiNLI","model":"ELC-BERT-small 24M","rank_in_archive_order":44,"of":67,"metrics":{"Matched":"79.2","Mismatched":"79.9"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-multinli","task":"Natural Language Inference","dataset":"MultiNLI","model":"LTG-BERT-small 24M","rank_in_archive_order":45,"of":67,"metrics":{"Matched":"78","Mismatched":"78.8"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"ELC-BERT-base 98M (zero init)","rank_in_archive_order":67,"of":90,"metrics":{"Accuracy":"63"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"ELC-BERT-small 24M","rank_in_archive_order":82,"of":90,"metrics":{"Accuracy":"55.4"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"LTG-BERT-base 98M","rank_in_archive_order":84,"of":90,"metrics":{"Accuracy":"54.7"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"LTG-BERT-small 24M","rank_in_archive_order":87,"of":90,"metrics":{"Accuracy":"53.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.02265","atlas_url":"https://app.syntology.ai/?focus=2311.02265","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2311.02265"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2311.02265\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2311.02265"},"call":"get_concepts_for_paper(arxiv_id=\"2311.02265\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5ddde2edf9df15538588687e6f65f10a12d345bb356f4aaf5cc5dce6dd6ae289","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}