arXiv cs.CL· Maher Pasa, Maria Hanini, Amro Najjar, Hasan Alkhder·· 12 小时前AI 评分22
alkhder 团队在 ImageEval 2026 共享任务中用约束选择与旋转平均 Logit 打分检测多模态幻觉
alkhder at ImageEval 2026 Shared Tasks: Constrained Selection and Rotation-Averaged Logit Scoring for Multimodal Hallucination Detection
AI 导读
alkhder 团队提交 ImageEval 2026 Subtask 1b 的方案，用预训练 7B 视觉语言模型零样本从三个候选陈述中选出与图像匹配的一项，无需任务特定训练或微调。
正文 · 原文
Abstract:We describe our submission to Subtask~1b of ImageEval 2026. The task consists of selecting the single visually valid statement from three candidates paired with an image, and is in both English and Modern Standard Arabic (MSA). Our system uses a pre-trained 7B vision--language model in a zero-shot setting, without task-specific training or fine-tuning. We formulate the task as a constrained selection problem and choose the answer using next-token log-probabilities. To reduce answer-position bias, we apply a Latin-square rotation to the candidate statements. Our system achieves CI scores of 0.0510 on the English test set and 0.0960 on the MSA test set, reducing CI relative to the official 3B baselines reported on devtest by 83.7\% and 80.4\%, respectively.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.22515 [cs.CL] |
| (or arXiv:2610.22515v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22515 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hasan Alkhder [view email]
[v1]
Thu, 15 Oct 2026 18:08:46 UTC (34 KB)
来源：arXiv cs.CL · arxiv.org