{"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/ernie-3-0-tiny-frustratingly-simple-method-to","title":"ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization","arxiv_id":"2301.03416","date":"2023-01-09","proceeding":null,"authors":["Weixin Liu","Xuyi Chen","Jiaxiang Liu","Shikun Feng","Yu Sun","Hao Tian","Hua Wu"],"abstract":"Task-agnostic knowledge distillation attempts to address the problem of deploying large pretrained language model in resource-constrained scenarios by compressing a large pretrained model called teacher into a smaller one called student such that the student can be directly finetuned on downstream tasks and retains comparable performance. However, we empirically find that there is a generalization gap between the student and the teacher in existing methods. In this work, we show that we can leverage multi-task learning in task-agnostic distillation to advance the generalization of the resulted student. In particular, we propose Multi-task Infused Task-agnostic Knowledge Distillation (MITKD). We first enhance the teacher by multi-task training it on multiple downstream tasks and then perform distillation to produce the student. Experimental results demonstrate that our method yields a student with much better generalization, significantly outperforms existing baselines, and establishes a new state-of-the-art result on in-domain, out-domain, and low-resource datasets in the setting of task-agnostic distillation. Moreover, our method even exceeds an 8x larger BERT$_{\\text{Base}}$ on SQuAD and four GLUE tasks. In addition, by combining ERNIE 3.0, our method achieves state-of-the-art results on 10 Chinese datasets.","url_abs":"https://arxiv.org/abs/2301.03416v1","url_pdf":"https://arxiv.org/pdf/2301.03416v1.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":"ernie-3-0-tiny-frustratingly-simple-method-to","repo_url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-tiny","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[{"method_slug":"ernie","method_name":"ERNIE"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.03416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.03416"}},"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/PaddlePaddle/PaddleNLP/tree/develop/model_zoo/ernie-tiny","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"5bab2794a9fc339f","entry":"cell_div","repo":"PaddlePaddle/PaddleNLP","repo_kind":"official","path":"paddlenlp/experimental/model_utils.py","file_url":"https://github.com/PaddlePaddle/PaddleNLP/blob/HEAD/paddlenlp/experimental/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5bab2794a9fc339f"}},{"code_sha256_prefix":"7667c4274e1b357d","entry":"load_vocabulary","repo":"PaddlePaddle/PaddleNLP","repo_kind":"official","path":"paddlenlp/experimental/model_utils.py","file_url":"https://github.com/PaddlePaddle/PaddleNLP/blob/HEAD/paddlenlp/experimental/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7667c4274e1b357d"}},{"code_sha256_prefix":"6db7f5c4fd955cff","entry":"sequence_mask","repo":"PaddlePaddle/PaddleNLP","repo_kind":"official","path":"paddlenlp/layers/sequence.py","file_url":"https://github.com/PaddlePaddle/PaddleNLP/blob/HEAD/paddlenlp/layers/sequence.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6db7f5c4fd955cff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}