Skip to content
conftrace_
2026 EMNLP EMNLP 2026

MSTree: Multi-Scale Evidence Tree for Training-Free Long-Form Video Question Answering

AbstractLong-form video question answering hinges on locating brief, sparse evidence buried in minutes of dense action. Flattening the entire video into a single caption stream forces the LLM to sift through thousands of tokens, where decisive cues are easily drowned out by surrounding context. We present MSTree, a training-free framework that organizes captions into a Multi-Scale Evidence Tree. The tree is built by a coordinated dual-modal segmentation method that combines visual scene transitions and textual coherence under temporal contiguity, producing segments that are both visually and semantically consistent. Inference follows a mine-then-reason workflow: the LLM first scans coarse segment summaries to locate the most relevant event, then reasons over its fine-grained captions. When the first-round prediction falls below a confidence threshold, Contrastive Targeted Reflection (CTR) activates. The model articulates a discriminative gap that specifies what evidence is still missing to separate the top candidate answers, and an answer-anchoring constraint requires any newly retrieved evidence to both support the revised prediction and contradict the original. On EgoSchema, NExT-QA, and Video-MME, MSTree reaches 68.4%, 77.5%, and 55.7% accuracy, outperforming all training-free baselines.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

More from EMNLP 2026

All EMNLP 2026 papers →