{"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/promptkd-distilling-student-friendly","title":"PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning","arxiv_id":"2402.12842","date":"2024-02-20","proceeding":null,"authors":["Gyeongman Kim","Doohyuk Jang","Eunho Yang"],"abstract":"Recent advancements in large language models (LLMs) have raised concerns about inference costs, increasing the need for research into model compression. While knowledge distillation (KD) is a prominent method for this, research on KD for generative language models like LLMs is relatively sparse, and the approach of distilling student-friendly knowledge, which has shown promising performance in KD for classification models, remains unexplored in generative language models. To explore this approach, we propose PromptKD, a simple yet effective method that utilizes prompt tuning - for the first time in KD - to enable generative language models to transfer student-friendly knowledge. Unlike previous works in classification that require fine-tuning the entire teacher model for extracting student-friendly knowledge, PromptKD achieves similar effects by adding a small number of prompt tokens and tuning only the prompt with student guidance. Extensive experiments on instruction-following datasets show that PromptKD achieves state-of-the-art performance while adding only 0.0007% of the teacher's parameters as prompts. Further analysis suggests that distilling student-friendly knowledge alleviates exposure bias effectively throughout the entire training process, leading to performance enhancements.","url_abs":"https://arxiv.org/abs/2402.12842v3","url_pdf":"https://arxiv.org/pdf/2402.12842v3.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":"promptkd-distilling-student-friendly","repo_url":"https://github.com/gmkim-ai/promptkd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"model-compression","task_name":"Model Compression"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"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":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"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=2402.12842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12842"}},"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/gmkim-ai/promptkd","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":"a692be6eb021f68d","entry":"add_data_args","repo":"gmkim-ai/promptkd","repo_kind":"official","path":"arguments.py","file_url":"https://github.com/gmkim-ai/promptkd/blob/HEAD/arguments.py","link_basis":"first_harvest_node","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":"a692be6eb021f68d"}},{"code_sha256_prefix":"de5974eab2121c2c","entry":"add_model_args","repo":"gmkim-ai/promptkd","repo_kind":"official","path":"arguments.py","file_url":"https://github.com/gmkim-ai/promptkd/blob/HEAD/arguments.py","link_basis":"first_harvest_node","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":"de5974eab2121c2c"}},{"code_sha256_prefix":"a2088913a75c72ec","entry":"calc_batch","repo":"gmkim-ai/promptkd","repo_kind":"official","path":"evaluate_exposure_bias.py","file_url":"https://github.com/gmkim-ai/promptkd/blob/HEAD/evaluate_exposure_bias.py","link_basis":"first_harvest_node","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":"a2088913a75c72ec"}},{"code_sha256_prefix":"61c5ad3a7b3c5731","entry":"exact_match","repo":"gmkim-ai/promptkd","repo_kind":"official","path":"rouge_metric.py","file_url":"https://github.com/gmkim-ai/promptkd/blob/HEAD/rouge_metric.py","link_basis":"first_harvest_node","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":"61c5ad3a7b3c5731"}},{"code_sha256_prefix":"a71327fc1087c21e","entry":"get_inputs","repo":"gmkim-ai/promptkd","repo_kind":"official","path":"evaluate_exposure_bias.py","file_url":"https://github.com/gmkim-ai/promptkd/blob/HEAD/evaluate_exposure_bias.py","link_basis":"first_harvest_node","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":"a71327fc1087c21e"}},{"code_sha256_prefix":"846c4335c1b51b91","entry":"get_learning_rate_scheduler","repo":"gmkim-ai/promptkd","repo_kind":"official","path":"train_promptkd.py","file_url":"https://github.com/gmkim-ai/promptkd/blob/HEAD/train_promptkd.py","link_basis":"first_harvest_node","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":"846c4335c1b51b91"}},{"code_sha256_prefix":"52a9f448d8cbd82a","entry":"normalize_answer","repo":"gmkim-ai/promptkd","repo_kind":"official","path":"rouge_metric.py","file_url":"https://github.com/gmkim-ai/promptkd/blob/HEAD/rouge_metric.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52a9f448d8cbd82a"}},{"code_sha256_prefix":"dda096fc09fd5f24","entry":"rouge","repo":"gmkim-ai/promptkd","repo_kind":"official","path":"rouge_metric.py","file_url":"https://github.com/gmkim-ai/promptkd/blob/HEAD/rouge_metric.py","link_basis":"first_harvest_node","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":"dda096fc09fd5f24"}},{"code_sha256_prefix":"3399622f0eac30dd","entry":"add_runtime_args","repo":"gmkim-ai/promptkd","repo_kind":"official","path":"arguments.py","file_url":"https://github.com/gmkim-ai/promptkd/blob/HEAD/arguments.py","link_basis":"first_harvest_node","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":"3399622f0eac30dd"}},{"code_sha256_prefix":"b0cb93ee3f5f771a","entry":"all_gather","repo":"gmkim-ai/promptkd","repo_kind":"official","path":"utils.py","file_url":"https://github.com/gmkim-ai/promptkd/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"b0cb93ee3f5f771a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}