NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video

Hugging Face Daily Papers Papers

Summary

NARU is a benchmark for evaluating narrative evolution and cultural reasoning in Japanese extreme long-form videos, constructed through a hierarchical annotation pipeline and native-speaker verification to address gaps in current benchmarks.

Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting social meaning that may remain implicit. However, existing benchmarks rarely evaluate these capabilities jointly, particularly in high-context, non-English media. To address this gap, we introduce NARU, a benchmark designed to evaluate Narrative evolution and Reasoning on cultural Understanding in Japanese long-form video. NARU consists of 1,481 questions grounded in 155 videos totaling 146.8 hours, spanning four narrative and five cultural dimensions. To construct the benchmark at this scale, we propose a hierarchical memory-based annotation pipeline that transforms raw video into structured event, narrative, and cultural annotations, then generates questions via task-oriented synthesis and iterative shortcut removal. The construction process includes two native-speaker verification stages involving 68 annotators. Evaluations across eight model configurations reveal substantial limitations in both long-range narrative integration and culturally grounded reasoning. By exposing these persistent gaps, NARU offers a systematic testing ground for developing MLLMs capable of reliably interpreting long-form, high-context video.
Original Article
View Cached Full Text

Cached at: 08/21/26, 12:09 PM

Paper page - NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video

Source: https://huggingface.co/papers/2608.13210

Abstract

NARU is a Japanese long-form video benchmark evaluating narrative evolution and cultural reasoning through a hierarchical annotation pipeline and extensive native-speaker verification.

Long-form video understandingencompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting social meaning that may remain implicit. However, existing benchmarks rarely evaluate these capabilities jointly, particularly in high-context, non-English media. To address this gap, we introduce NARU, a benchmark designed to evaluateNarrative evolutionand Reasoning on cultural Understanding in Japanese long-form video. NARU consists of 1,481 questions grounded in 155 videos totaling 146.8 hours, spanning four narrative and five cultural dimensions. To construct the benchmark at this scale, we propose ahierarchical memory-based annotationpipeline that transforms raw video into structured event, narrative, and cultural annotations, then generates questions viatask-oriented synthesisand iterativeshortcut removal. The construction process includes two native-speaker verification stages involving 68 annotators. Evaluations across eight model configurations reveal substantial limitations in both long-range narrative integration and culturally grounded reasoning. By exposing these persistent gaps, NARU offers a systematic testing ground for developingMLLMscapable of reliably interpreting long-form, high-context video.

View arXiv pageView PDFProject pageGitHub3Add to collection

Get this paper in your agent:

hf papers read 2608\.13210

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.13210 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.13210 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.13210 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

NARRA-Gym for Evaluating Interactive Narrative Agents

arXiv cs.CL

This paper introduces NARRA-Gym, a benchmark and executable evaluation environment for assessing Large Language Models' abilities in sustaining interactive narratives, managing memory, and adapting to users over multiple turns.

Show HN: FastUbu – An Ultrafast Video Archive

Hacker News Top

FastUbu is a tool that applies modern AI techniques like indexing and transcription to the 30-year-old Ubu film archive, aiming to provide ultrafast video processing via the Kino API.