analiza aiqbench
This paper introduces an auditable pipeline using vision-language models and OCR to construct provenance-rich knowledge graphs from lecture videos, specifically targeting neural network education content. By validating concepts against multimodal evidence rather than relying solely on transcripts, the method achieves high retrieval accuracy while ensuring factual grounding in complex technical domains. The work advances AI applications for educational reasoning by shifting focus toward verifiable information extraction over pure performance metrics.
Evidence-Grounded Multimodal Knowledge Graph Construction for Multi-Lecture Educational Reasoning
arXiv:2608.03161v1 Announce Type: cross Abstract: Lecture videos distribute knowledge across speech, slide text, diagrams, equations, and presentation order, which transcript-only retrieval does not fully preserve. This paper presents an evidence-grounded multimodal pipeline that transcribes lectures, selects semantic anchors, applies optical character recognition (OCR), and uses a vision-language model to extract only concepts and typed relationships supported by transcript, OCR, or visual evidence. Mentions are validated and canonicalized into a provenance-rich knowledge graph. On three neural-network lectures, the pipeline processed 3,118 frames, 756 transcript segments, and 559 anchors. It retained 1,022 concept and 312 relationship mentions, yielding 172 canonical concepts and 282 relationships with 90.38% endpoint coverage. A preliminary three question retrieval test achieved 100% top-1 and top-3 accuracy and 100% mean top-5 recall. The contribution is an auditable construction method rather than a state-of-the-art performance claim.
Abstract:Lecture videos distribute knowledge across speech, slide text, diagrams, equations, and presentation order, which transcript-only retrieval does not fully preserve. This paper presents an evidence-grounded multimodal pipeline that transcribes lectures, selects semantic anchors, applies optical character recognition (OCR), and uses a vision-language model to extract only concepts and typed relationships supported by transcript, OCR, or visual evidence. Mentions are validated and canonicalized into a provenance-rich knowledge graph. On three neural-network lectures, the pipeline processed 3,118 frames, 756 transcript segments, and 559 anchors. It retained 1,022 concept and 312 relationship mentions, yielding 172 canonical concepts and 282 relationships with 90.38% endpoint coverage. A preliminary three question retrieval test achieved 100% top-1 and top-3 accuracy and 100% mean top-5 recall. The contribution is an auditable construction method rather than a state-of-the-art performance claim.
Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
arXiv:2608.03161 [cs.AI]
(or arXiv:2608.03161v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.03161 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 229 cuvinte
Subiecte conexe
GraphLoom: Reliability-Calibrated Graph Evidence Routing for Multimodal KG-RAG
arXiv · 18 aug. 2026
VISPATH: Visual-Intent-Guided Path Reasoning for Multimodal Knowledge Graph Question Answering
arXiv · 21 sept. 2026
From Vector Search to Agentic RAG: Building an Enterprise Research Analyst with hipVS
AMD · 15 iul. 2026
CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation
arXiv · 9 sept. 2026