cs.CVNov 16, 2026

Does the Model Use What It Cites? Counterfactual Tests of Grounded Reasoning Chains in Small Video-Language Models

Authors: Jugal Gajjar, Kamalasankari Subramaniakuppusamy

Organizations: Independent Researchers

Abstract

A grounded reasoning chain cites a frame span and a box for every step, so a reader can check where the model looked. Whether the answer depends on the cited region is a different question. We test it by intervention: the regions a model cited in its own chain are blacked out, and the share of correct answers that flip is compared with blacking out boxes of the same size elsewhere on the same frames. The paired difference, the cite gap, needs no annotation. We apply it to 2-3B video-language models trained on exact CLEVRER chains and on pseudo-labelled NExT-QA chains. With the same weights, the cite gap is 0.089 on CLEVRER and 0.003 on NExT-QA. Pooled over models, masking the cited boxes flips 2.2 times as many correct answers as the control on CLEVRER and 1.1 times as many on NExT-QA, also among the answers that depend on the video at all, while the boxes pass a grounding check on both. Masking the cited entity on every frame, instead of the cited box, flips 1.9 times as many answers as its control. The NExT-QA chains were supervised to cite two frames of entities that stay visible on most frames, so this outcome is what the supervision predicts; the point is that the usual check on grounded chains cannot see it. A citation can be verifiable and relevant without the answer depending on it, and a test of grounded reasoning should remove what a chain names, not only where it points.

Figures & tables

Appendix figures & tables25 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Chains That See, Answers That Don't: A Multi-Aspect Evaluation Recipe for Forced Chain-of-Thought on Video-MME

    Jun 22, 2026Zhichao Fan, Yanhang Li, Zexin ZhuangVLM EvaluationVideo Question Answering

  2. ChainReaction: Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answering

    Aug 28, 2025Paritosh Parmar, Eric Peh, Basura FernandoVideo Question AnsweringMultimodal CoT Reasoning