arXiv cs.CL· Yiheng Wang, Yueqian Lin, Lichen Zhu, Yudong Liu, Hai "Helen" Li, Yiran Chen·· 12 小时前AI 评分42
当没有正确答案时：诊断 MLLMs 在视频理解中的缺失答案检测能力
When No Answer Is Correct: Diagnosing Absent Answer Detection for MLLMs in Video Understanding
AI 导读
一项诊断性研究发现，多模态大语言模型（MLLMs）在视频理解中面对候选选项均不正确的情况时，绝大多数会挑选看似合理的干扰项，而非识别出“无正确答案”。该失败在时序推理任务中更明显，且随帧采样密度提高而加剧。思维链提示虽能显著提升检测率，但整体表现仍不理想，说明仅靠提示策略不足以解决这一系统性缺陷。
正文 · 原文
Abstract:Multimodal large language models (MLLMs) have made substantial advancements in video understanding, yet the reliability of their responses remains underexplored. This work presents a diagnostic study of absent answer detection for MLLMs in video understanding, where the correct answer is deliberately excluded from the candidate set and a reliable model is expected to recognize that no valid option exists. We evaluate the absent answer detection behavior under three settings: multiple-choice questions augmented with a ``None of the Above'' option, open-ended generation with a detection instruction, and standard evaluation without any guidance. Across a diverse set of models and benchmarks, we find that MLLMs overwhelmingly select plausible distractors rather than detecting the absent answer. This failure is more pronounced in temporal reasoning tasks and worsens with denser frame sampling. We further explore chain-of-thought prompting as a mitigation strategy and find that while it substantially improves detection rates, performance remains unsatisfactory, suggesting that prompting-based strategies alone are insufficient to fully address this limitation. These findings expose a systematic failure in absent answer detection and highlight the need for explicit detection mechanisms in multimodal systems.
| Comments: | Published as a conference paper at EMNLP 2026 |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2606.08239 [cs.AI] |
| (or arXiv:2606.08239v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.08239 arXiv-issued DOI via DataCite |
Submission history
From: Yiheng Wang [view email]
[v1]
Sat, 6 Jun 2026 15:51:25 UTC (581 KB)
[v2]
Mon, 2 Nov 2026 03:48:28 UTC (587 KB)
来源：arXiv cs.CL · arxiv.org