{"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/list-lite-self-training-makes-efficient-few-1","title":"LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot Learners","arxiv_id":"2110.06274","date":"2021-10-12","proceeding":"Findings (NAACL) 2022 7","authors":["Yaqing Wang","Subhabrata Mukherjee","Xiaodong Liu","Jing Gao","Ahmed Hassan Awadallah","Jianfeng Gao"],"abstract":"We present a new method LiST is short for Lite Prompted Self-Training for parameter-efficient fine-tuning of large pre-trained language models (PLMs) for few-shot learning. LiST improves over recent methods that adopt prompt-based fine-tuning (FN) using two key techniques. The first is the use of self-training to leverage large amounts of unlabeled data for prompt-based FN in few-shot settings. We use self-training in conjunction with meta-learning for re-weighting noisy pseudo-prompt labels. Self-training is expensive as it requires updating all the model parameters repetitively. Therefore, we use a second technique for light-weight fine-tuning where we introduce a small number of task-specific parameters that are fine-tuned during self-training while keeping the PLM encoder frozen. Our experiments show that LiST can effectively leverage unlabeled data to improve the model performance for few-shot learning. Additionally, the fine-tuning is efficient as it only updates a small percentage of parameters and the overall model footprint is reduced since several tasks can share a common PLM encoder as backbone. A comprehensive study on six NLU tasks demonstrate LiST to improve by 35% over classic fine-tuning and 6% over prompt-based FN with 96% reduction in number of trainable parameters when fine-tuned with no more than 30 labeled examples from each task. With only 14M tunable parameters, LiST outperforms GPT-3 in-context learning by 33% on few-shot NLU tasks.","url_abs":"https://arxiv.org/abs/2110.06274v2","url_pdf":"https://arxiv.org/pdf/2110.06274v2.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":"list-lite-self-training-makes-efficient-few-1","repo_url":"https://github.com/microsoft/list","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.06274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06274"}},"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/microsoft/list","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran":3,"ran_fixture":2,"unverified":5},"by_repo_kind":{"official":{"samples":12,"ran":7,"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":"e448786d5ff1875a","entry":"default_dev_objective","repo":"microsoft/list","repo_kind":"official","path":"src/trainer.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/trainer.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e448786d5ff1875a"}},{"code_sha256_prefix":"417ac95acb8c20b4","entry":"generate_noise","repo":"microsoft/list","repo_kind":"official","path":"src/models.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"417ac95acb8c20b4"}},{"code_sha256_prefix":"e768e25ca95f70cd","entry":"input_example_to_string","repo":"microsoft/list","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e768e25ca95f70cd"}},{"code_sha256_prefix":"fbef70dc7c700501","entry":"input_example_to_tuple","repo":"microsoft/list","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbef70dc7c700501"}},{"code_sha256_prefix":"b69b1ad29fd21db5","entry":"select_neighbors","repo":"microsoft/list","repo_kind":"official","path":"src/label_search.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/label_search.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b69b1ad29fd21db5"}},{"code_sha256_prefix":"7b0111630cee9629","entry":"stable_kl","repo":"microsoft/list","repo_kind":"official","path":"src/loss.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/loss.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b0111630cee9629"}},{"code_sha256_prefix":"b62076c5483738dc","entry":"text_classification_metrics","repo":"microsoft/list","repo_kind":"official","path":"src/processors.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/processors.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b62076c5483738dc"}},{"code_sha256_prefix":"3e6d40262bdef1d5","entry":"entropy","repo":"microsoft/list","repo_kind":"official","path":"src/loss.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/loss.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":"3e6d40262bdef1d5"}},{"code_sha256_prefix":"47923f36537f5f79","entry":"eval_pairing_acc","repo":"microsoft/list","repo_kind":"official","path":"src/label_search.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/label_search.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":"47923f36537f5f79"}},{"code_sha256_prefix":"b9836599a17cd3c0","entry":"norm_grad","repo":"microsoft/list","repo_kind":"official","path":"src/models.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/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":"b9836599a17cd3c0"}},{"code_sha256_prefix":"be6b57168b0424f3","entry":"select_likely_words","repo":"microsoft/list","repo_kind":"official","path":"src/label_search.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/label_search.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":"be6b57168b0424f3"}},{"code_sha256_prefix":"71af7b8adce2cf48","entry":"tokenize_multipart_input","repo":"microsoft/list","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/microsoft/list/blob/HEAD/src/dataset.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":"71af7b8adce2cf48"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}