{"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/figcaps-hf-a-figure-to-caption-generative","title":"FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback","arxiv_id":"2307.10867","date":"2023-07-20","proceeding":null,"authors":["Ashish Singh","Prateek Agarwal","Zixuan Huang","Arpita Singh","Tong Yu","Sungchul Kim","Victor Bursztyn","Nikos Vlassis","Ryan A. Rossi"],"abstract":"Captions are crucial for understanding scientific visualizations and documents. Existing captioning methods for scientific figures rely on figure-caption pairs extracted from documents for training, many of which fall short with respect to metrics like helpfulness, explainability, and visual-descriptiveness [15] leading to generated captions being misaligned with reader preferences. To enable the generation of high-quality figure captions, we introduce FigCaps-HF a new framework for figure-caption generation that can incorporate domain expert feedback in generating captions optimized for reader preferences. Our framework comprises of 1) an automatic method for evaluating quality of figure-caption pairs, 2) a novel reinforcement learning with human feedback (RLHF) method to optimize a generative figure-to-caption model for reader preferences. We demonstrate the effectiveness of our simple learning framework by improving performance over standard fine-tuning across different types of models. In particular, when using BLIP as the base model, our RLHF framework achieves a mean gain of 35.7%, 16.9%, and 9% in ROUGE, BLEU, and Meteor, respectively. Finally, we release a large-scale benchmark dataset with human feedback on figure-caption pairs to enable further evaluation and development of RLHF techniques for this problem.","url_abs":"https://arxiv.org/abs/2307.10867v1","url_pdf":"https://arxiv.org/pdf/2307.10867v1.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":"figcaps-hf-a-figure-to-caption-generative","repo_url":"https://github.com/figcapshf/figcapshf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"caption-generation","task_name":"Caption Generation"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"blip","method_name":"BLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2307.10867","atlas_url":"https://app.syntology.ai/?focus=2307.10867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10867"}},"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/figcapshf/figcapshf","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"c6ec173f19f5c34d","entry":"interpolate_pos_embed","repo":"figcapshf/figcapshf","repo_kind":"official","path":"models/vit.py","file_url":"https://github.com/figcapshf/figcapshf/blob/HEAD/models/vit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c6ec173f19f5c34d"}},{"code_sha256_prefix":"aa5a91226269bf75","entry":"tile","repo":"figcapshf/figcapshf","repo_kind":"official","path":"models/blip_vqa.py","file_url":"https://github.com/figcapshf/figcapshf/blob/HEAD/models/blip_vqa.py","link_basis":"harvester_set","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":"aa5a91226269bf75"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"figcapshf/figcapshf","repo_kind":"official","path":"models/blip_retrieval.py","file_url":"https://github.com/figcapshf/figcapshf/blob/HEAD/models/blip_retrieval.py","link_basis":"harvester_set","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":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"73cecca9f3575f09","entry":"concat_all_gather","repo":"figcapshf/figcapshf","repo_kind":"official","path":"models/blip_pretrain.py","file_url":"https://github.com/figcapshf/figcapshf/blob/HEAD/models/blip_pretrain.py","link_basis":"harvester_set","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":"73cecca9f3575f09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}