{"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/learning-hierarchical-prompt-with-structured","title":"Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models","arxiv_id":"2312.06323","date":"2023-12-11","proceeding":null,"authors":["Yubin Wang","Xinyang Jiang","De Cheng","Dongsheng Li","Cairong Zhao"],"abstract":"Prompt learning has become a prevalent strategy for adapting vision-language foundation models to downstream tasks. As large language models (LLMs) have emerged, recent studies have explored the use of category-related descriptions as input to enhance prompt effectiveness. Nevertheless, conventional descriptions fall short of structured information that effectively represents the interconnections among entities or attributes linked to a particular category. To address this limitation and prioritize harnessing structured knowledge, this paper advocates for leveraging LLMs to build a graph for each description to model the entities and attributes describing the category, as well as their correlations. Preexisting prompt tuning methods exhibit inadequacies in managing this structured knowledge. Consequently, we propose a novel approach called Hierarchical Prompt Tuning (HPT), which enables simultaneous modeling of both structured and conventional linguistic knowledge. Specifically, we introduce a relationship-guided attention module to capture pair-wise associations among entities and attributes for low-level prompt learning. In addition, by incorporating high-level and global-level prompts modeling overall semantics, the proposed hierarchical structure forges cross-level interlinks and empowers the model to handle more complex and long-term relationships. Extensive experiments demonstrate that our HPT shows strong effectiveness and generalizes much better than existing SOTA methods. Our code is available at https://github.com/Vill-Lab/2024-AAAI-HPT.","url_abs":"https://arxiv.org/abs/2312.06323v1","url_pdf":"https://arxiv.org/pdf/2312.06323v1.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":"learning-hierarchical-prompt-with-structured","repo_url":"https://github.com/vill-lab/2024-aaai-hpt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-hierarchical-prompt-with-structured","repo_url":"https://github.com/ThomasWangY/2024-AAAI-HPT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"prompt-learning","task_name":"Prompt Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/prompt-engineering-on-caltech-101","task":"Prompt Engineering","dataset":"Caltech-101","model":"HPT","rank_in_archive_order":5,"of":14,"metrics":{"Harmonic mean":"96.65"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-dtd","task":"Prompt Engineering","dataset":"DTD","model":"HPT","rank_in_archive_order":7,"of":14,"metrics":{"Harmonic mean":"72.16"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-eurosat","task":"Prompt Engineering","dataset":"EuroSAT","model":"HPT","rank_in_archive_order":8,"of":14,"metrics":{"Harmonic mean":"84.82"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-fgvc-aircraft","task":"Prompt Engineering","dataset":"FGVC-Aircraft","model":"HPT","rank_in_archive_order":6,"of":14,"metrics":{"Harmonic mean":"40.28"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-food-101","task":"Prompt Engineering","dataset":"Food-101","model":"HPT","rank_in_archive_order":11,"of":13,"metrics":{"Harmonic mean":"91.01"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet","task":"Prompt Engineering","dataset":"ImageNet","model":"HPT","rank_in_archive_order":7,"of":15,"metrics":{"Harmonic mean":"74.17"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-v2","task":"Prompt Engineering","dataset":"ImageNet V2","model":"HPT","rank_in_archive_order":2,"of":8,"metrics":{"Top-1 accuracy %":"65.25"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-a","task":"Prompt Engineering","dataset":"ImageNet-A","model":"HPT","rank_in_archive_order":6,"of":9,"metrics":{"Top-1 accuracy %":"50.85"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-r","task":"Prompt Engineering","dataset":"ImageNet-R","model":"HPT","rank_in_archive_order":6,"of":9,"metrics":{"Top-1 accuracy %":"77.38"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-imagenet-s","task":"Prompt Engineering","dataset":"ImageNet-S","model":"HPT","rank_in_archive_order":4,"of":9,"metrics":{"Top-1 accuracy %":"49.36"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-oxford-102-flower","task":"Prompt Engineering","dataset":"Oxford 102 Flower","model":"HPT","rank_in_archive_order":2,"of":14,"metrics":{"Harmonic mean":"87.16"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-oxford-iiit-pet-dataset","task":"Prompt Engineering","dataset":"Oxford-IIIT Pet Dataset","model":"HPT","rank_in_archive_order":5,"of":14,"metrics":{"Harmonic mean":"96.71"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-sun397","task":"Prompt Engineering","dataset":"SUN397","model":"HPT","rank_in_archive_order":7,"of":14,"metrics":{"Harmonic mean":"80.88"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-stanford-cars-1","task":"Prompt Engineering","dataset":"Stanford Cars","model":"HPT","rank_in_archive_order":9,"of":14,"metrics":{"Harmonic mean":"75.57"},"uses_additional_data":false},{"leaderboard":"/sota/prompt-engineering-on-ucf101","task":"Prompt Engineering","dataset":"UCF101","model":"HPT","rank_in_archive_order":6,"of":14,"metrics":{"Harmonic mean":"83.16"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.06323","atlas_url":"https://app.syntology.ai/?focus=2312.06323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06323"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/vill-lab/2024-aaai-hpt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ThomasWangY/2024-AAAI-HPT","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":"98f385d847636a3e","entry":"basic_clean","repo":"vill-lab/2024-aaai-hpt","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/vill-lab/2024-aaai-hpt/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"vill-lab/2024-aaai-hpt","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/vill-lab/2024-aaai-hpt/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"vill-lab/2024-aaai-hpt","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/vill-lab/2024-aaai-hpt/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"fc48e485e5a826d4","entry":"build_model","repo":"vill-lab/2024-aaai-hpt","repo_kind":"official","path":"clip/model.py","file_url":"https://github.com/vill-lab/2024-aaai-hpt/blob/HEAD/clip/model.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":"fc48e485e5a826d4"}},{"code_sha256_prefix":"fbf8c0143d9c48e3","entry":"load","repo":"vill-lab/2024-aaai-hpt","repo_kind":"official","path":"clip/clip.py","file_url":"https://github.com/vill-lab/2024-aaai-hpt/blob/HEAD/clip/clip.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":"fbf8c0143d9c48e3"}},{"code_sha256_prefix":"440f24d0f7a85c28","entry":"multi_head_attention_forward","repo":"vill-lab/2024-aaai-hpt","repo_kind":"official","path":"clip/attention.py","file_url":"https://github.com/vill-lab/2024-aaai-hpt/blob/HEAD/clip/attention.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":"440f24d0f7a85c28"}},{"code_sha256_prefix":"b5d0d43936dc7a5c","entry":"softmax","repo":"vill-lab/2024-aaai-hpt","repo_kind":"official","path":"clip/attention.py","file_url":"https://github.com/vill-lab/2024-aaai-hpt/blob/HEAD/clip/attention.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":"b5d0d43936dc7a5c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}