{"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/vision-and-language-or-vision-for-language-on","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","arxiv_id":"2109.04448","date":"2021-09-09","proceeding":"EMNLP 2021 11","authors":["Stella Frank","Emanuele Bugliarello","Desmond Elliott"],"abstract":"Pretrained vision-and-language BERTs aim to learn representations that combine information from both modalities. We propose a diagnostic method based on cross-modal input ablation to assess the extent to which these models actually integrate cross-modal information. This method involves ablating inputs from one modality, either entirely or selectively based on cross-modal grounding alignments, and evaluating the model prediction performance on the other modality. Model performance is measured by modality-specific tasks that mirror the model pretraining objectives (e.g. masked language modelling for text). Models that have learned to construct cross-modal representations using both modalities are expected to perform worse when inputs are missing from a modality. We find that recently proposed models have much greater relative difficulty predicting text when visual information is ablated, compared to predicting visual object categories when text is ablated, indicating that these models are not symmetrically cross-modal.","url_abs":"https://arxiv.org/abs/2109.04448v1","url_pdf":"https://arxiv.org/pdf/2109.04448v1.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":"vision-and-language-or-vision-for-language-on","repo_url":"https://github.com/e-bug/cross-modal-ablation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"vision-and-language-or-vision-for-language-on","repo_url":"https://github.com/e-bug/volta","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"vision-and-language-or-vision-for-language-on","repo_url":"https://github.com/ivana-13/guided_masking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"vision-and-language-or-vision-for-language-on","repo_url":"https://github.com/shin-ee-chen/bla","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.04448","atlas_url":"https://app.syntology.ai/?focus=2109.04448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04448"}},"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/ivana-13/guided_masking","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shin-ee-chen/bla","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/e-bug/volta","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/e-bug/cross-modal-ablation","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1},"listed":{"samples":1,"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":"fef294a1e5404f0c","entry":"get_index_positions","repo":"ivana-13/guided_masking","repo_kind":"listed","path":"SVO_probes_word_clouds.py","file_url":"https://github.com/ivana-13/guided_masking/blob/HEAD/SVO_probes_word_clouds.py","link_basis":"harvester_set","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":"fef294a1e5404f0c"}},{"code_sha256_prefix":"e0ae1e24559ddd25","entry":"get_sentence_data","repo":"e-bug/cross-modal-ablation","repo_kind":"official","path":"volta/volta/datasets/flickr30ke_ablation_dataset.py","file_url":"https://github.com/e-bug/cross-modal-ablation/blob/HEAD/volta/volta/datasets/flickr30ke_ablation_dataset.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":"e0ae1e24559ddd25"}},{"code_sha256_prefix":"a7ee1c19d2e17999","entry":"iot","repo":"e-bug/cross-modal-ablation","repo_kind":"official","path":"volta/volta/datasets/flickr30ke_ablation_dataset.py","file_url":"https://github.com/e-bug/cross-modal-ablation/blob/HEAD/volta/volta/datasets/flickr30ke_ablation_dataset.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":"a7ee1c19d2e17999"}},{"code_sha256_prefix":"a1bd52099cee7c87","entry":"iou","repo":"e-bug/cross-modal-ablation","repo_kind":"official","path":"volta/volta/datasets/flickr30ke_ablation_dataset.py","file_url":"https://github.com/e-bug/cross-modal-ablation/blob/HEAD/volta/volta/datasets/flickr30ke_ablation_dataset.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":"a1bd52099cee7c87"}},{"code_sha256_prefix":"a2faafba33358747","entry":"kl_1601","repo":"e-bug/cross-modal-ablation","repo_kind":"official","path":"volta/volta/losses.py","file_url":"https://github.com/e-bug/cross-modal-ablation/blob/HEAD/volta/volta/losses.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":"a2faafba33358747"}},{"code_sha256_prefix":"1adf127958517c64","entry":"mse_2048","repo":"e-bug/cross-modal-ablation","repo_kind":"official","path":"volta/volta/losses.py","file_url":"https://github.com/e-bug/cross-modal-ablation/blob/HEAD/volta/volta/losses.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":"1adf127958517c64"}},{"code_sha256_prefix":"60cab169db54e986","entry":"nce_2048","repo":"e-bug/cross-modal-ablation","repo_kind":"official","path":"volta/volta/losses.py","file_url":"https://github.com/e-bug/cross-modal-ablation/blob/HEAD/volta/volta/losses.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":"60cab169db54e986"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}