{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/encoder-vs-decoder-comparative-analysis-of","title":"Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks","arxiv_id":"2406.13469","date":"2024-06-19","proceeding":null,"authors":["Dan Saattrup Nielsen","Kenneth Enevoldsen","Peter Schneider-Kamp"],"abstract":"This paper explores the performance of encoder and decoder language models on multilingual Natural Language Understanding (NLU) tasks, with a broad focus on Germanic languages. Building upon the ScandEval benchmark, initially restricted to evaluating encoder models, we extend the evaluation framework to include decoder models. We introduce a method for evaluating decoder models on NLU tasks and apply it to the languages Danish, Swedish, Norwegian, Icelandic, Faroese, German, Dutch, and English. Through a series of experiments and analyses, we also address research questions regarding the comparative performance of encoder and decoder models, the impact of NLU task types, and the variation across language resources. Our findings reveal that encoder models can achieve significantly better NLU performance than decoder models despite having orders of magnitude fewer parameters. Additionally, we investigate the correlation between decoders and task performance via a UMAP analysis, shedding light on the unique capabilities of decoder and encoder models. This study contributes to a deeper understanding of language model paradigms in NLU tasks and provides valuable insights for model selection and evaluation in multilingual settings.","url_abs":"https://arxiv.org/abs/2406.13469v2","url_pdf":"https://arxiv.org/pdf/2406.13469v2.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":[{"paper_slug":"encoder-vs-decoder-comparative-analysis-of","repo_url":"https://github.com/ScandEval/ScandEval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"encoder-vs-decoder-comparative-analysis-of","repo_url":"https://github.com/saattrupdan/scandeval","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"encoder-vs-decoder-comparative-analysis-of","repo_url":"https://github.com/MS-P3/code7/tree/main/vision_text_dual_encoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"model-selection","task_name":"Model Selection"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.13469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13469"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ScandEval/ScandEval","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MS-P3/code7/tree/main/vision_text_dual_encoder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/saattrupdan/scandeval","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"76fd1517c3722774","entry":"get_closest_match","repo":"ScandEval/ScandEval","repo_kind":"listed","path":"src/euroeval/closest_match.py","file_url":"https://github.com/ScandEval/ScandEval/blob/HEAD/src/euroeval/closest_match.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"76fd1517c3722774"}},{"code_sha256_prefix":"7e78af0cca343023","entry":"get_package_version","repo":"ScandEval/ScandEval","repo_kind":"listed","path":"src/euroeval/data_models.py","file_url":"https://github.com/ScandEval/ScandEval/blob/HEAD/src/euroeval/data_models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e78af0cca343023"}},{"code_sha256_prefix":"c77577a25a058035","entry":"load_custom_datasets_module","repo":"ScandEval/ScandEval","repo_kind":"listed","path":"src/euroeval/custom_dataset_configs.py","file_url":"https://github.com/ScandEval/ScandEval/blob/HEAD/src/euroeval/custom_dataset_configs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c77577a25a058035"}},{"code_sha256_prefix":"4d6e325649536cf4","entry":"load_data","repo":"ScandEval/ScandEval","repo_kind":"listed","path":"src/euroeval/data_loading.py","file_url":"https://github.com/ScandEval/ScandEval/blob/HEAD/src/euroeval/data_loading.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d6e325649536cf4"}},{"code_sha256_prefix":"009eb05ddfea0cb3","entry":"load_raw_data","repo":"ScandEval/ScandEval","repo_kind":"listed","path":"src/euroeval/data_loading.py","file_url":"https://github.com/ScandEval/ScandEval/blob/HEAD/src/euroeval/data_loading.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"009eb05ddfea0cb3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}