Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2026

Abstract

Video Large Language Models (Vid-LLMs) have demonstrated remarkable performance in video understanding tasks, yet their robustness under conversational interaction remains largely underexplored. In this paper, we identify spatiotemporal sycophancy, a failure mode in which Vid-LLMs retract initially correct, visually grounded judgments and conform to misleading user feedback under negation-based gaslighting. Rather than merely changing their answers, the models often fabricate unsupported temporal or spatial explanations to justify incorrect revisions. To systematically investigate this phenomenon, we propose a negation-based gaslighting evaluation framework and introduce GasVideo-1000, a curated benchmark designed to probe spatiotemporal sycophancy with clear visual grounding and temporal reasoning requirements. We evaluate a broad range of state-of-the-art open-source and proprietary Vid-LLMs across diverse video understanding tasks. Extensive experiments reveal that vulnerability to negation-based gaslighting is pervasive and severe, even among models with strong baseline performance. While prompt-level grounding constraints can partially mitigate this behavior, they do not reliably prevent hallucinated justifications or belief reversal. Our results indicate that current Vid-LLMs lack robust mechanisms for maintaining grounded spatiotemporal beliefs under adversarial conversational feedback.

Discipline

Artificial Intelligence and Robotics | Information Security

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), San Diego, California, July 2-7

First Page

14836

Last Page

14852

Identifier

10.18653/v1/2026.findings-acl.729

Publisher

ACL

City or Country

San Diego, California

Additional URL

https://doi.org/10.18653/v1/2026.findings-acl.729

Download

Share

COinS