arXiv cs.CL· Clemencia Siro, Laura Hollink·· 13 小时前AI 评分22
更多元数据反而误导：LLM 生成博物馆描述中的字段级接地问题研究
When More Metadata Misleads: Probing Field-Level Grounding in LLM-Generated Museum Descriptions
AI 导读
一项被 EMNLP 2026 Findings 接收的研究通过两阶段框架考察元数据构成如何影响 LLM 生成文物描述，发现元数据数量本身并不能解释生成行为。字段类型决定模型是接地、省略还是推断信息，图像既可能支持视觉接地，也可能增加无依据的解读。作者据此主张元数据条件的数据到文本评测应评估字段级与断言级支持，而非仅依赖输入覆盖率或参考相似度。
正文 · 原文
Abstract:Metadata-conditioned generation is often framed as a data-to-text task in which additional input fields should improve grounding. Museum description generation challenges this assumption because catalogue records are heterogeneous, partially visual, and unevenly documented across geographic regions. We study how metadata composition shapes the generation of artefact descriptions through a two-phase framework. Phase 1 analyses natural metadata variation in a large museum collection, where field count, field type, image availability, and Place co-vary. Phase 2 introduces controlled field probes that hold object identity fixed while varying metadata quantity, field type, and image access. Our results show that metadata quantity alone does not explain generation behaviour. Field type determines whether models ground, omit, or infer information, while images can both support visual grounding and increase unsupported interpretation. More broadly, our findings show that metadata-conditioned data-to-text evaluation should assess field- and claim-level support, rather than relying only on aggregate input coverage or reference similarity.
| Comments: | Accepted to EMNLP 2026 Findings |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Digital Libraries (cs.DL); Machine Learning (cs.LG) |
| ACM classes: | I.2.7; H.3.1 |
| Cite as: | arXiv:2610.31193 [cs.CL] |
| (or arXiv:2610.31193v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31193 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Clemencia Siro [view email]
[v1]
Thu, 22 Oct 2026 12:41:12 UTC (4,457 KB)
来源：arXiv cs.CL · arxiv.org