{"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/on-the-consistency-of-video-large-language","title":"On the Consistency of Video Large Language Models in Temporal Comprehension","arxiv_id":"2411.12951","date":"2024-11-20","proceeding":"CVPR 2025 1","authors":["Minjoon Jung","Junbin Xiao","Byoung-Tak Zhang","Angela Yao"],"abstract":"Video large language models (Video-LLMs) can temporally ground language queries and retrieve video moments. Yet, such temporal comprehension capabilities are neither well-studied nor understood. So we conduct a study on prediction consistency -- a key indicator for robustness and trustworthiness of temporal grounding. After the model identifies an initial moment within the video content, we apply a series of probes to check if the model's responses align with this initial grounding as an indicator of reliable comprehension. Our results reveal that current Video-LLMs are sensitive to variations in video contents, language queries, and task settings, unveiling severe deficiencies in maintaining consistency. We further explore common prompting and instruction-tuning methods as potential solutions, but find that their improvements are often unstable. To that end, we propose event temporal verification tuning that explicitly accounts for consistency, and demonstrate significant improvements for both grounding and consistency. Our data and code will be available at https://github.com/minjoong507/Consistency-of-Video-LLM.","url_abs":"https://arxiv.org/abs/2411.12951v1","url_pdf":"https://arxiv.org/pdf/2411.12951v1.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":"on-the-consistency-of-video-large-language","repo_url":"https://github.com/minjoong507/consistency-of-video-llm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2411.12951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12951"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/minjoong507/consistency-of-video-llm","reach":{"status":"ok"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":6,"samples":[{"code_sha256_prefix":"c51f78ff0e556f67","entry":"convert_source_vicuna_format","repo":"minjoong507/consistency-of-video-llm","repo_kind":"official","path":"timechat/datasets/datasets/video_instruct_dataset.py","file_url":"https://github.com/minjoong507/consistency-of-video-llm/blob/HEAD/timechat/datasets/datasets/video_instruct_dataset.py","link_basis":"first_harvest_node","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":"c51f78ff0e556f67"}},{"code_sha256_prefix":"6205e41e68ab3848","entry":"crop","repo":"minjoong507/consistency-of-video-llm","repo_kind":"official","path":"timechat/processors/functional_video.py","file_url":"https://github.com/minjoong507/consistency-of-video-llm/blob/HEAD/timechat/processors/functional_video.py","link_basis":"first_harvest_node","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":"6205e41e68ab3848"}},{"code_sha256_prefix":"fe43cafec19fc16d","entry":"interpolate_frame_pos_embed","repo":"minjoong507/consistency-of-video-llm","repo_kind":"official","path":"timechat/processors/video_processor.py","file_url":"https://github.com/minjoong507/consistency-of-video-llm/blob/HEAD/timechat/processors/video_processor.py","link_basis":"first_harvest_node","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":"fe43cafec19fc16d"}},{"code_sha256_prefix":"140fbef36559768e","entry":"preprocess_multimodal","repo":"minjoong507/consistency-of-video-llm","repo_kind":"official","path":"timechat/datasets/datasets/video_instruct_dataset.py","file_url":"https://github.com/minjoong507/consistency-of-video-llm/blob/HEAD/timechat/datasets/datasets/video_instruct_dataset.py","link_basis":"first_harvest_node","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":"140fbef36559768e"}},{"code_sha256_prefix":"f1f9c7dfbe0b3105","entry":"resize","repo":"minjoong507/consistency-of-video-llm","repo_kind":"official","path":"timechat/processors/functional_video.py","file_url":"https://github.com/minjoong507/consistency-of-video-llm/blob/HEAD/timechat/processors/functional_video.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":"f1f9c7dfbe0b3105"}},{"code_sha256_prefix":"d0e65b9f687e2f97","entry":"resized_crop","repo":"minjoong507/consistency-of-video-llm","repo_kind":"official","path":"timechat/processors/functional_video.py","file_url":"https://github.com/minjoong507/consistency-of-video-llm/blob/HEAD/timechat/processors/functional_video.py","link_basis":"first_harvest_node","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":"d0e65b9f687e2f97"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}