{"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/right-this-way-can-vlms-guide-us-to-see-more","title":"Right this way: Can VLMs Guide Us to See More to Answer Questions?","arxiv_id":"2411.00394","date":"2024-11-01","proceeding":null,"authors":["Li Liu","Diji Yang","Sijia Zhong","Kalyana Suma Sree Tholeti","Lei Ding","Yi Zhang","Leilani H. Gilpin"],"abstract":"In question-answering scenarios, humans can assess whether the available information is sufficient and seek additional information if necessary, rather than providing a forced answer. In contrast, Vision Language Models (VLMs) typically generate direct, one-shot responses without evaluating the sufficiency of the information. To investigate this gap, we identify a critical and challenging task in the Visual Question Answering (VQA) scenario: can VLMs indicate how to adjust an image when the visual information is insufficient to answer a question? This capability is especially valuable for assisting visually impaired individuals who often need guidance to capture images correctly. To evaluate this capability of current VLMs, we introduce a human-labeled dataset as a benchmark for this task. Additionally, we present an automated framework that generates synthetic training data by simulating ``where to know'' scenarios. Our empirical results show significant performance improvements in mainstream VLMs when fine-tuned with this synthetic data. This study demonstrates the potential to narrow the gap between information assessment and acquisition in VLMs, bringing their performance closer to humans.","url_abs":"https://arxiv.org/abs/2411.00394v1","url_pdf":"https://arxiv.org/pdf/2411.00394v1.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":"right-this-way-can-vlms-guide-us-to-see-more","repo_url":"https://github.com/LeoLee7/Directional_guidance","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.00394","atlas_url":"https://app.syntology.ai/?focus=2411.00394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00394"}},"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":"deterministic:regex_extraction","url":"https://github.com/LeoLee7/Directional_guidance","reach":null}],"summary":{"ran_fixture":3,"ran_violates":1,"unverified":13},"by_repo_kind":{"official":{"samples":15,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"c5dd104ff54b0ca2","entry":"cut_offset_effect","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c5dd104ff54b0ca2"}},{"code_sha256_prefix":"99a42f1554ad7f02","entry":"offset","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99a42f1554ad7f02"}},{"code_sha256_prefix":"763f6fe20bd52fbb","entry":"parse_score","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"763f6fe20bd52fbb"}},{"code_sha256_prefix":"55c32993da87759b","entry":"unpad_image","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"55c32993da87759b"}},{"code_sha256_prefix":"f59afa008df86cb0","entry":"batch_inference_on_synthetic_images_and_save_to_csv","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.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":"f59afa008df86cb0"}},{"code_sha256_prefix":"fe2ff17e14b57e11","entry":"caption_image_instructblip_hf_batch_inference","repo":"leolee7/directional_guidance","repo_kind":"official","path":"vlm_inference.py","file_url":"https://github.com/leolee7/directional_guidance/blob/HEAD/vlm_inference.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":"fe2ff17e14b57e11"}},{"code_sha256_prefix":"0df5aedc4a3fea99","entry":"generate_img","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.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":"0df5aedc4a3fea99"}},{"code_sha256_prefix":"1cd05a89f739ec8d","entry":"generate_synthetic_images","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.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":"1cd05a89f739ec8d"}},{"code_sha256_prefix":"1c8fe25bb724da3e","entry":"handle_blip2_inference","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.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":"1c8fe25bb724da3e"}},{"code_sha256_prefix":"feb83db5b84c6095","entry":"handle_instructblip_inference","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.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":"feb83db5b84c6095"}},{"code_sha256_prefix":"83d591a37eb3dad8","entry":"handle_llava_hf_inference","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.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":"83d591a37eb3dad8"}},{"code_sha256_prefix":"ed1656e8949887df","entry":"handle_llava_official_inference","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.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":"ed1656e8949887df"}},{"code_sha256_prefix":"43fe617b5b69bfcd","entry":"inference_on_synthetic_images_and_save_to_csv","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.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":"43fe617b5b69bfcd"}},{"code_sha256_prefix":"2ca535421a0f566a","entry":"main","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.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":"2ca535421a0f566a"}},{"code_sha256_prefix":"106e86b62b7730cb","entry":"zoom_in","repo":"leolee7/directional_guidance","repo_kind":"official","path":"data_augmentation/functions.py","file_url":"https://github.com/leolee7/directional_guidance/blob/HEAD/data_augmentation/functions.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":"106e86b62b7730cb"}},{"code_sha256_prefix":"1234d349895eec44","entry":"zoom_in_offset_effect","repo":"leolee7/directional_guidance","repo_kind":"official","path":"data_augmentation/functions.py","file_url":"https://github.com/leolee7/directional_guidance/blob/HEAD/data_augmentation/functions.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":"1234d349895eec44"}},{"code_sha256_prefix":"b63f58cc49b0a7b7","entry":"zoom_in_offset_effect","repo":"LeoLee7/Directional_guidance","repo_kind":"official","path":"generate_train_dataset_main.py","file_url":"https://github.com/LeoLee7/Directional_guidance/blob/HEAD/generate_train_dataset_main.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":"b63f58cc49b0a7b7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}