{"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/cofipara-a-coarse-to-fine-paradigm-for","title":"CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models","arxiv_id":"2405.00390","date":"2024-05-01","proceeding":null,"authors":["Hongzhan Lin","Zixin Chen","Ziyang Luo","Mingfei Cheng","Jing Ma","Guang Chen"],"abstract":"Social media abounds with multimodal sarcasm, and identifying sarcasm targets is particularly challenging due to the implicit incongruity not directly evident in the text and image modalities. Current methods for Multimodal Sarcasm Target Identification (MSTI) predominantly focus on superficial indicators in an end-to-end manner, overlooking the nuanced understanding of multimodal sarcasm conveyed through both the text and image. This paper proposes a versatile MSTI framework with a coarse-to-fine paradigm, by augmenting sarcasm explainability with reasoning and pre-training knowledge. Inspired by the powerful capacity of Large Multimodal Models (LMMs) on multimodal reasoning, we first engage LMMs to generate competing rationales for coarser-grained pre-training of a small language model on multimodal sarcasm detection. We then propose fine-tuning the model for finer-grained sarcasm target identification. Our framework is thus empowered to adeptly unveil the intricate targets within multimodal sarcasm and mitigate the negative impact posed by potential noise inherently in LMMs. Experimental results demonstrate that our model far outperforms state-of-the-art MSTI methods, and markedly exhibits explainability in deciphering sarcasm as well.","url_abs":"https://arxiv.org/abs/2405.00390v2","url_pdf":"https://arxiv.org/pdf/2405.00390v2.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":"cofipara-a-coarse-to-fine-paradigm-for","repo_url":"https://github.com/lbotirx/cofipara","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"},{"task_slug":"sarcasm-detection","task_name":"Sarcasm Detection"},{"task_slug":"small-language-model","task_name":"Small Language Model"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.00390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00390"}},"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":"deterministic:regex_extraction","url":"https://github.com/wjq-learning/MSTI","reach":null}],"summary":{"ran":17,"unverified":4},"by_repo_kind":{"found_in_text":{"samples":21,"ran":17,"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":21,"samples":[{"code_sha256_prefix":"7302832cca671b08","entry":"BertAttention","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7302832cca671b08"}},{"code_sha256_prefix":"fc89405716521d69","entry":"BertSelfAttention","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fc89405716521d69"}},{"code_sha256_prefix":"8412d3cacea13366","entry":"BertSelfOutput","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8412d3cacea13366"}},{"code_sha256_prefix":"1911487cd9e73ab2","entry":"ConvTranspose_Bn_Activation","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1911487cd9e73ab2"}},{"code_sha256_prefix":"21f26a2563ea4990","entry":"Conv_Bn_Activation","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"21f26a2563ea4990"}},{"code_sha256_prefix":"335a1bcec2ef9fe9","entry":"Conv_Transformer1","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"335a1bcec2ef9fe9"}},{"code_sha256_prefix":"de226e1a2d9129e4","entry":"Conv_Transformer3","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"de226e1a2d9129e4"}},{"code_sha256_prefix":"e2ebf44083133a57","entry":"DownSample1","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e2ebf44083133a57"}},{"code_sha256_prefix":"848c1f779fedf979","entry":"DownSample2","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"848c1f779fedf979"}},{"code_sha256_prefix":"21380bb333b0d7c6","entry":"DownSample3","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"21380bb333b0d7c6"}},{"code_sha256_prefix":"b16c558f2f074d24","entry":"DownSample4","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b16c558f2f074d24"}},{"code_sha256_prefix":"9b0e1a32e8d880ef","entry":"DownSample5","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9b0e1a32e8d880ef"}},{"code_sha256_prefix":"93bd978679041497","entry":"Mish","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"93bd978679041497"}},{"code_sha256_prefix":"e3230f56904b248c","entry":"Neck","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e3230f56904b248c"}},{"code_sha256_prefix":"0bd649dbeed2fb62","entry":"ResBlock","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0bd649dbeed2fb62"}},{"code_sha256_prefix":"c950ce52821790da","entry":"Upsample","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c950ce52821790da"}},{"code_sha256_prefix":"48207b4ab02a3332","entry":"Yolov4Head","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"48207b4ab02a3332"}},{"code_sha256_prefix":"f218f7507ca4156e","entry":"Config","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f218f7507ca4156e"}},{"code_sha256_prefix":"63e1e3501a6b8376","entry":"Conv_Transformer2","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"63e1e3501a6b8376"}},{"code_sha256_prefix":"24ef62fa3750f770","entry":"MSTD","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"24ef62fa3750f770"}},{"code_sha256_prefix":"b80a6e1f98069d41","entry":"Yolov4","repo":"wjq-learning/MSTI","repo_kind":"found_in_text","path":"model.py","file_url":"https://github.com/wjq-learning/MSTI/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b80a6e1f98069d41"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}