{"url":"/dataset/next-gqa","name":"NExT-GQA","full_name":null,"description_markdown":"We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video-language understanding. Specifically, by forcing vision-language models (VLMs) to answer questions and simultaneously provide visual evidence, we seek to ascertain the extent to which the predictions of such techniques are genuinely anchored in relevant video content, versus spurious correlations from language or irrelevant visual context. Towards this, we construct NExT-GQA -- an extension of NExT-QA with 10.5K temporal grounding (or location) labels tied to the original QA pairs. With NExT-GQA, we scrutinize a variety of state-of-the-art VLMs. Through post-hoc attention analysis, we find that these models are weak in substantiating the answers despite their strong QA performance. This exposes a severe limitation of these models in making reliable predictions.","description_withheld":null,"homepage":"https://github.com/doc-doc/next-gqa","introduced_date":"2023-09-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/can-i-trust-your-answer-visually-grounded","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","first_author":"Junbin Xiao","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Zero-Shot Video Question Answer","url":"/task/zeroshot-video-question-answer","datasets_with_task":"/datasets/task/zeroshot-video-question-answer"}],"languages":[],"variants":["NExT-GQA"],"data_loaders":[],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-gqa","task":"Zero-Shot Video Question Answer","dataset_variant":"NExT-GQA","rows":9,"metrics":["Acc@GQA"],"first_row_in_archive_order":{"model":"DeVi (Gemini 2.0)","paper":"/paper/question-answering-dense-video-events","metrics":{"Acc@GQA":"28.9"},"code_links":[{"title":"qhuni/deve-qa","url":"https://github.com/qhuni/deve-qa"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/videomind-a-chain-of-lora-agent-for-long","title":"VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning","date":"2025-03-17","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/question-answering-dense-video-events","title":"Question-Answering Dense Video Events","date":"2024-09-06","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/streaming-long-video-understanding-with-large","title":"Streaming Long Video Understanding with Large Language Models","date":"2024-05-25","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/language-repository-for-long-video","title":"Language Repository for Long Video Understanding","date":"2024-03-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":9,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-simple-llm-framework-for-long-range-video","title":"A Simple LLM Framework for Long-Range Video Question-Answering","date":"2023-12-28","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mistral-7b","title":"Mistral 7B","date":"2023-10-10","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":9,"samples_unverified":2,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":4,"samples_harvested":30,"samples_ran":27,"samples_unverified":3,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}