{"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/the-bla-benchmark-investigating-basic","title":"The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models","arxiv_id":"2310.15061","date":"2023-10-23","proceeding":null,"authors":["Xinyi Chen","Raquel Fernández","Sandro Pezzelle"],"abstract":"Despite the impressive performance achieved by pre-trained language-and-vision models in downstream tasks, it remains an open question whether this reflects a proper understanding of image-text interaction. In this work, we explore to what extent they handle basic linguistic constructions -- active-passive voice, coordination, and relative clauses -- that even preschool children can typically master. We present BLA, a novel, automatically constructed benchmark to evaluate multimodal models on these Basic Language Abilities. We show that different types of Transformer-based systems, such as CLIP, ViLBERT, and BLIP2, generally struggle with BLA in a zero-shot setting, in line with previous findings. Our experiments, in particular, show that most of the tested models only marginally benefit when fine-tuned or prompted with construction-specific samples. Yet, the generative BLIP2 shows promising trends, especially in an in-context learning setting. This opens the door to using BLA not only as an evaluation benchmark but also to improve models' basic language abilities.","url_abs":"https://arxiv.org/abs/2310.15061v1","url_pdf":"https://arxiv.org/pdf/2310.15061v1.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":"the-bla-benchmark-investigating-basic","repo_url":"https://github.com/shin-ee-chen/bla","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"vilbert","method_name":"ViLBERT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.15061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15061"}},"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/shin-ee-chen/bla","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/shin-ee-chen/BLA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":3,"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":12,"ran":11,"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":"aa81d03f07735ab8","entry":"compute_acc","repo":"shin-ee-chen/BLA","repo_kind":"official","path":"evaluation_models/blip2/utils.py","file_url":"https://github.com/shin-ee-chen/BLA/blob/HEAD/evaluation_models/blip2/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa81d03f07735ab8"}},{"code_sha256_prefix":"ad12a494674d23fb","entry":"compute_n_params","repo":"shin-ee-chen/BLA","repo_kind":"official","path":"evaluation_models/blip2/utils.py","file_url":"https://github.com/shin-ee-chen/BLA/blob/HEAD/evaluation_models/blip2/utils.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":"ad12a494674d23fb"}},{"code_sha256_prefix":"574b247caf8962a7","entry":"get_accuracy","repo":"shin-ee-chen/BLA","repo_kind":"official","path":"evaluation_models/clip/utils.py","file_url":"https://github.com/shin-ee-chen/BLA/blob/HEAD/evaluation_models/clip/utils.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":"574b247caf8962a7"}},{"code_sha256_prefix":"53d7a74c79b94312","entry":"in_concext_learning_prompt","repo":"shin-ee-chen/bla","repo_kind":"official","path":"evaluation_models/blip2/test_blip2_bla.py","file_url":"https://github.com/shin-ee-chen/bla/blob/HEAD/evaluation_models/blip2/test_blip2_bla.py","link_basis":"first_harvest_node","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":"53d7a74c79b94312"}},{"code_sha256_prefix":"c7f85279d772ea19","entry":"itm_eval","repo":"shin-ee-chen/BLA","repo_kind":"official","path":"evaluation_models/blip2/train_retrieval.py","file_url":"https://github.com/shin-ee-chen/BLA/blob/HEAD/evaluation_models/blip2/train_retrieval.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c7f85279d772ea19"}},{"code_sha256_prefix":"e19e22cd7641eb82","entry":"itm_eval","repo":"shin-ee-chen/BLA","repo_kind":"official","path":"evaluation_models/blip2/eval_retrieval_video.py","file_url":"https://github.com/shin-ee-chen/BLA/blob/HEAD/evaluation_models/blip2/eval_retrieval_video.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":"e19e22cd7641eb82"}},{"code_sha256_prefix":"e564057cbee4961d","entry":"load_image","repo":"shin-ee-chen/BLA","repo_kind":"official","path":"evaluation_models/blip2/predict.py","file_url":"https://github.com/shin-ee-chen/BLA/blob/HEAD/evaluation_models/blip2/predict.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":"e564057cbee4961d"}},{"code_sha256_prefix":"56d99aa0cb0fac0a","entry":"prompt_question","repo":"shin-ee-chen/bla","repo_kind":"official","path":"evaluation_models/blip2/test_blip2_bla.py","file_url":"https://github.com/shin-ee-chen/bla/blob/HEAD/evaluation_models/blip2/test_blip2_bla.py","link_basis":"first_harvest_node","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":"56d99aa0cb0fac0a"}},{"code_sha256_prefix":"b880398cd04cf6f1","entry":"read_json_file","repo":"shin-ee-chen/BLA","repo_kind":"official","path":"evaluation_models/blip2/bla_utils.py","file_url":"https://github.com/shin-ee-chen/BLA/blob/HEAD/evaluation_models/blip2/bla_utils.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":"b880398cd04cf6f1"}},{"code_sha256_prefix":"1af344b6a7a0e6fb","entry":"read_json_file_as_dict","repo":"shin-ee-chen/BLA","repo_kind":"official","path":"evaluation_models/blip2/bla_utils.py","file_url":"https://github.com/shin-ee-chen/BLA/blob/HEAD/evaluation_models/blip2/bla_utils.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":"1af344b6a7a0e6fb"}},{"code_sha256_prefix":"e7c98e8f0375bb0f","entry":"show_image","repo":"shin-ee-chen/BLA","repo_kind":"official","path":"evaluation_models/clip/utils.py","file_url":"https://github.com/shin-ee-chen/BLA/blob/HEAD/evaluation_models/clip/utils.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":"e7c98e8f0375bb0f"}},{"code_sha256_prefix":"ca409984e9ca8111","entry":"load_demo_image","repo":"shin-ee-chen/BLA","repo_kind":"official","path":"evaluation_models/blip2/bla_utils.py","file_url":"https://github.com/shin-ee-chen/BLA/blob/HEAD/evaluation_models/blip2/bla_utils.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":"ca409984e9ca8111"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}