{"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/soft-prompting-with-graph-of-thought-for","title":"Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning","arxiv_id":"2404.04538","date":"2024-04-06","proceeding":null,"authors":["Juncheng Yang","Zuchao Li","Shuai Xie","Wei Yu","Shijun Li","Bo Du"],"abstract":"The chain-of-thought technique has been received well in multi-modal tasks. It is a step-by-step linear reasoning process that adjusts the length of the chain to improve the performance of generated prompts. However, human thought processes are predominantly non-linear, as they encompass multiple aspects simultaneously and employ dynamic adjustment and updating mechanisms. Therefore, we propose a novel Aggregation-Graph-of-Thought (AGoT) mechanism for soft-prompt tuning in multi-modal representation learning. The proposed AGoT models the human thought process not only as a chain but also models each step as a reasoning aggregation graph to cope with the overlooked multiple aspects of thinking in single-step reasoning. This turns the entire reasoning process into prompt aggregation and prompt flow operations. Experiments show that our multi-modal model enhanced with AGoT soft-prompting achieves good results in several tasks such as text-image retrieval, visual question answering, and image recognition. In addition, we demonstrate that it has good domain generalization performance due to better reasoning.","url_abs":"https://arxiv.org/abs/2404.04538v1","url_pdf":"https://arxiv.org/pdf/2404.04538v1.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":"soft-prompting-with-graph-of-thought-for","repo_url":"https://github.com/shishicode/agot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.04538","atlas_url":"https://app.syntology.ai/?focus=2404.04538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04538"}},"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/shishicode/agot","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"official":{"samples":9,"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":"e758ef19d32b8b11","entry":"adapter_func","repo":"shishicode/agot","repo_kind":"official","path":"trainers/petl_factory.py","file_url":"https://github.com/shishicode/agot/blob/HEAD/trainers/petl_factory.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":"e758ef19d32b8b11"}},{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"shishicode/agot","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/shishicode/agot/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":"ba26afd892405335","entry":"compute_ci95","repo":"shishicode/agot","repo_kind":"official","path":"parse_test_res.py","file_url":"https://github.com/shishicode/agot/blob/HEAD/parse_test_res.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":"ba26afd892405335"}},{"code_sha256_prefix":"d858deb1b3a2d3ba","entry":"cross_entropy","repo":"shishicode/agot","repo_kind":"official","path":"trainers/AGoT.py","file_url":"https://github.com/shishicode/agot/blob/HEAD/trainers/AGoT.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":"d858deb1b3a2d3ba"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"shishicode/agot","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/shishicode/agot/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":"a75e6ade7e6f9240","entry":"softmax_gating","repo":"shishicode/agot","repo_kind":"official","path":"trainers/petl_factory.py","file_url":"https://github.com/shishicode/agot/blob/HEAD/trainers/petl_factory.py","link_basis":"first_harvest_node","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":"a75e6ade7e6f9240"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"shishicode/agot","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/shishicode/agot/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":"c47aa9e5b049a11d","entry":"build_model","repo":"shishicode/agot","repo_kind":"official","path":"clip/model.py","file_url":"https://github.com/shishicode/agot/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":"c47aa9e5b049a11d"}},{"code_sha256_prefix":"fbf8c0143d9c48e3","entry":"load","repo":"shishicode/agot","repo_kind":"official","path":"clip/clip.py","file_url":"https://github.com/shishicode/agot/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"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}