{"task":"Image Captioning","dataset":"Object HalBench","metric_names":["chair_i","chair_s"],"rows":[{"id":47249,"task":"Image Captioning","parent_task":null,"dataset":"Object HalBench","model_name":"RLHF-V","metrics":{"chair_i":"7.5","chair_s":"12.2"},"paper_url":"https://arxiv.org/abs/2312.00849v2","paper_title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","paper_date":"2023-12-01","code_links":[{"title":"openbmb/minicpm-v","url":"https://github.com/openbmb/minicpm-v"},{"title":"rlhf-v/rlhf-v","url":"https://github.com/rlhf-v/rlhf-v"},{"title":"tidedra/vl-rlhf","url":"https://github.com/tidedra/vl-rlhf"},{"title":"exgc/r1v-free","url":"https://github.com/exgc/r1v-free"}],"metrics_order":"[\"chair_i\", \"chair_s\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47250,"task":"Image Captioning","parent_task":null,"dataset":"Object HalBench","model_name":"RLAIF-V 7B","metrics":{"chair_i":"4.3","chair_s":"8.5"},"paper_url":"https://arxiv.org/abs/2405.17220v2","paper_title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","paper_date":"2024-05-27","code_links":[{"title":"openbmb/minicpm-v","url":"https://github.com/openbmb/minicpm-v"},{"title":"openbmb/omnilmm","url":"https://github.com/openbmb/omnilmm"},{"title":"OpenBMB/MiniCPM-o","url":"https://github.com/OpenBMB/MiniCPM-o"},{"title":"rlhf-v/rlaif-v","url":"https://github.com/rlhf-v/rlaif-v"},{"title":"rlhf-v/rlhf-v","url":"https://github.com/rlhf-v/rlhf-v"}],"metrics_order":"[\"chair_i\", \"chair_s\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":47251,"task":"Image Captioning","parent_task":null,"dataset":"Object HalBench","model_name":"RLAIF-V 12B","metrics":{"chair_i":"1.8","chair_s":"3.3"},"paper_url":"https://arxiv.org/abs/2405.17220v2","paper_title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","paper_date":"2024-05-27","code_links":[{"title":"openbmb/minicpm-v","url":"https://github.com/openbmb/minicpm-v"},{"title":"openbmb/omnilmm","url":"https://github.com/openbmb/omnilmm"},{"title":"OpenBMB/MiniCPM-o","url":"https://github.com/OpenBMB/MiniCPM-o"},{"title":"rlhf-v/rlaif-v","url":"https://github.com/rlhf-v/rlaif-v"},{"title":"rlhf-v/rlhf-v","url":"https://github.com/rlhf-v/rlhf-v"}],"metrics_order":"[\"chair_i\", \"chair_s\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}