{"id":"W4404781890","doi":"10.18653/v1/2024.findings-emnlp.191","title":"Are Large Vision Language Models up to the Challenge of Chart Comprehension and Reasoning","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Centre International de Recherche sur le Cancer","keywords":"Computer science; Comprehension; Chart; Natural language processing; Artificial intelligence; Programming language; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005869419,0.0009888357,0.000610455,0.0008754093,0.0004826349,0.004497285,0.002457212,0.001987877,0.007141515],"category_scores_gemma":[0.04115385,0.000638946,0.001539959,0.0005124339,0.001654716,0.01123362,0.002935786,0.003549477,0.003404449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00185696,"about_ca_system_score_gemma":0.002962284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004917643,"about_ca_topic_score_gemma":0.004928255,"domain_scores_codex":[0.9952334,0.002348359,0.0002754371,0.0009475222,0.0009985287,0.000196834],"domain_scores_gemma":[0.9805558,0.0128746,0.001072237,0.002810073,0.002100176,0.00058706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001120379,0.0007341995,0.007702484,0.002828121,0.0002990989,0.000792985,0.009733825,0.05662319,0.03969303,0.1309869,0.1160206,0.6334652],"study_design_scores_gemma":[0.0002669613,0.0004791623,0.003038311,0.0007500394,0.0002327104,0.0006301675,0.003798612,0.550606,0.03335205,0.2485363,0.1580599,0.0002497971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07205354,0.001578173,0.8419558,0.01079457,0.0005368591,0.0005907737,0.003449502,0.05095688,0.01808396],"genre_scores_gemma":[0.4544051,0.00102653,0.5250527,0.003260311,0.0001990349,0.0007663693,0.00711504,0.003172544,0.005002451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007141515,"threshold_uncertainty_score":0.03104085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01876255332833101,"score_gpt":0.3026275532543308,"score_spread":0.2838649999259998,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}