{"url":"/task/factual-inconsistency-detection-in-chart","name":"Factual Inconsistency Detection in Chart Captioning","slug":"factual-inconsistency-detection-in-chart","description_markdown":"Detect factual inconsistency between charts and captions.","categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":4,"papers_with_code":4,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/factual-inconsistency-detection-in-chart-1","slug":"factual-inconsistency-detection-in-chart-1","dataset":"CHOCOLATE-LLM","dataset_url":"/dataset/chocolate","rows_in_archive":5,"metrics":["Kendall's Tau-c"],"first_row_in_archive_order":{"model":"GPT-4V","paper_title":"GPT-4 Technical Report","paper_url":"/paper/gpt-4-technical-report-1","paper_date":"2023-03-15","arxiv_id":"2303.08774","code_links":[{"title":"openai/evals","url":"https://github.com/openai/evals"},{"title":"shmsw25/factscore","url":"https://github.com/shmsw25/factscore"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"gpt4life/alpagasus","url":"https://github.com/gpt4life/alpagasus"},{"title":"emrgnt-cmplxty/zero-shot-replication","url":"https://github.com/emrgnt-cmplxty/zero-shot-replication"},{"title":"ethz-privsec/superhuman-ai-consistency","url":"https://github.com/ethz-privsec/superhuman-ai-consistency"},{"title":"ethz-spylab/superhuman-ai-consistency","url":"https://github.com/ethz-spylab/superhuman-ai-consistency"},{"title":"eternityyw/tram-benchmark","url":"https://github.com/eternityyw/tram-benchmark"},{"title":"AUCOHL/RTL-Repo","url":"https://github.com/AUCOHL/RTL-Repo"},{"title":"zach-zhiling-zheng/reticular_chemist","url":"https://github.com/zach-zhiling-zheng/reticular_chemist"},{"title":"lflage/openfactscore","url":"https://github.com/lflage/openfactscore"}],"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":1}}},{"leaderboard":"/sota/factual-inconsistency-detection-in-chart-2","slug":"factual-inconsistency-detection-in-chart-2","dataset":"CHOCOLATE-FT","dataset_url":"/dataset/chocolate","rows_in_archive":5,"metrics":["Kendall's Tau-c"],"first_row_in_archive_order":{"model":"Bard (before Gemini)","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/factual-inconsistency-detection-in-chart-3","slug":"factual-inconsistency-detection-in-chart-3","dataset":"CHOCOLATE-LVLM","dataset_url":"/dataset/chocolate","rows_in_archive":5,"metrics":["Kendall's Tau-c"],"first_row_in_archive_order":{"model":"ChartVE","paper_title":"Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning","paper_url":"/paper/do-lvlms-understand-charts-analyzing-and","paper_date":"2023-12-15","arxiv_id":"2312.10160","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforceairesearch/crmarena","url":"https://github.com/salesforceairesearch/crmarena"},{"title":"khuangaf/chocolate","url":"https://github.com/khuangaf/chocolate"}],"syntology":null}},{"leaderboard":"/sota/factual-inconsistency-detection-in-chart","slug":"factual-inconsistency-detection-in-chart","dataset":"CHOCOLATE","dataset_url":"/dataset/chocolate","rows_in_archive":1,"metrics":["Kendall's Tau-c"],"first_row_in_archive_order":{"model":"ChartVE","paper_title":"Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning","paper_url":"/paper/do-lvlms-understand-charts-analyzing-and","paper_date":"2023-12-15","arxiv_id":"2312.10160","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforceairesearch/crmarena","url":"https://github.com/salesforceairesearch/crmarena"},{"title":"khuangaf/chocolate","url":"https://github.com/khuangaf/chocolate"}],"syntology":null}}],"datasets":[{"url":"/dataset/chocolate","name":"CHOCOLATE","full_name":"Captions Have Often ChOsen Lies About The Evidence","num_papers_in_archive":4}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":4,"of":4,"tagged_in_all":4,"items":[{"url":"/paper/gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/improved-baselines-with-visual-instruction","title":"Improved Baselines with Visual Instruction Tuning","date":"2023-10-05","arxiv_id":"2310.03744","repositories_listed":9,"syntology":{"n":9,"n_ran":6,"n_unverified":3,"n_pointer_only":8}},{"url":"/paper/do-lvlms-understand-charts-analyzing-and","title":"Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning","date":"2023-12-15","arxiv_id":"2312.10160","repositories_listed":3,"syntology":null},{"url":"/paper/deplot-one-shot-visual-language-reasoning-by","title":"DePlot: One-shot visual language reasoning by plot-to-table translation","date":"2022-12-20","arxiv_id":"2212.10505","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}