{"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/mm-shap-a-performance-agnostic-metric-for","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks","arxiv_id":"2212.08158","date":"2022-12-15","proceeding":null,"authors":["Letitia Parcalabescu","Anette Frank"],"abstract":"Vision and language models (VL) are known to exploit unrobust indicators in individual modalities (e.g., introduced by distributional biases) instead of focusing on relevant information in each modality. That a unimodal model achieves similar accuracy on a VL task to a multimodal one, indicates that so-called unimodal collapse occurred. However, accuracy-based tests fail to detect e.g., when the model prediction is wrong, while the model used relevant information from a modality. Instead, we propose MM-SHAP, a performance-agnostic multimodality score based on Shapley values that reliably quantifies in which proportions a multimodal model uses individual modalities. We apply MM-SHAP in two ways: (1) to compare models for their average degree of multimodality, and (2) to measure for individual models the contribution of individual modalities for different tasks and datasets. Experiments with six VL models -- LXMERT, CLIP and four ALBEF variants -- on four VL tasks highlight that unimodal collapse can occur to different degrees and in different directions, contradicting the wide-spread assumption that unimodal collapse is one-sided. Based on our results, we recommend MM-SHAP for analysing multimodal tasks, to diagnose and guide progress towards multimodal integration. Code available at \\url{https://github.com/Heidelberg-NLP/MM-SHAP}.","url_abs":"https://arxiv.org/abs/2212.08158v2","url_pdf":"https://arxiv.org/pdf/2212.08158v2.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":"mm-shap-a-performance-agnostic-metric-for","repo_url":"https://github.com/heidelberg-nlp/mm-shap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"albef","method_name":"ALBEF"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"lxmert","method_name":"LXMERT"},{"method_slug":"fail","method_name":"fail"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.08158","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08158"}},"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/heidelberg-nlp/mm-shap","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":9},"by_repo_kind":{"official":{"samples":10,"ran":1,"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":"e3c7e31f2f094463","entry":"is_1d","repo":"heidelberg-nlp/mm-shap","repo_kind":"official","path":"shap/_explanation.py","file_url":"https://github.com/heidelberg-nlp/mm-shap/blob/HEAD/shap/_explanation.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":"e3c7e31f2f094463"}},{"code_sha256_prefix":"aa6dc1f66baa0c61","entry":"boston","repo":"heidelberg-nlp/mm-shap","repo_kind":"official","path":"shap/datasets.py","file_url":"https://github.com/heidelberg-nlp/mm-shap/blob/HEAD/shap/datasets.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":"aa6dc1f66baa0c61"}},{"code_sha256_prefix":"7b3ebcfb23ea11c3","entry":"coef","repo":"heidelberg-nlp/mm-shap","repo_kind":"official","path":"shap/benchmark/methods.py","file_url":"https://github.com/heidelberg-nlp/mm-shap/blob/HEAD/shap/benchmark/methods.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":"7b3ebcfb23ea11c3"}},{"code_sha256_prefix":"ac2cc0a75031d92f","entry":"compute_output_dims","repo":"heidelberg-nlp/mm-shap","repo_kind":"official","path":"shap/_explanation.py","file_url":"https://github.com/heidelberg-nlp/mm-shap/blob/HEAD/shap/_explanation.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":"ac2cc0a75031d92f"}},{"code_sha256_prefix":"71e360cbf88d5730","entry":"identity","repo":"heidelberg-nlp/mm-shap","repo_kind":"official","path":"shap/links.py","file_url":"https://github.com/heidelberg-nlp/mm-shap/blob/HEAD/shap/links.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":"71e360cbf88d5730"}},{"code_sha256_prefix":"796121b410630901","entry":"imagenet50","repo":"heidelberg-nlp/mm-shap","repo_kind":"official","path":"shap/datasets.py","file_url":"https://github.com/heidelberg-nlp/mm-shap/blob/HEAD/shap/datasets.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":"796121b410630901"}},{"code_sha256_prefix":"ab3ccac5c5ddaa3d","entry":"linear_shap_corr","repo":"heidelberg-nlp/mm-shap","repo_kind":"official","path":"shap/benchmark/methods.py","file_url":"https://github.com/heidelberg-nlp/mm-shap/blob/HEAD/shap/benchmark/methods.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":"ab3ccac5c5ddaa3d"}},{"code_sha256_prefix":"10fe6a267963961d","entry":"linear_shap_ind","repo":"heidelberg-nlp/mm-shap","repo_kind":"official","path":"shap/benchmark/methods.py","file_url":"https://github.com/heidelberg-nlp/mm-shap/blob/HEAD/shap/benchmark/methods.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":"10fe6a267963961d"}},{"code_sha256_prefix":"dc32c75aaf993f9f","entry":"linnerud","repo":"heidelberg-nlp/mm-shap","repo_kind":"official","path":"shap/datasets.py","file_url":"https://github.com/heidelberg-nlp/mm-shap/blob/HEAD/shap/datasets.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":"dc32c75aaf993f9f"}},{"code_sha256_prefix":"bb689134796e145f","entry":"logit","repo":"heidelberg-nlp/mm-shap","repo_kind":"official","path":"shap/links.py","file_url":"https://github.com/heidelberg-nlp/mm-shap/blob/HEAD/shap/links.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":"bb689134796e145f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}