首页/数据集/Multimodal alignment degradation measured by CLIP score.

Multimodal alignment degradation measured by CLIP score.

Figshare2026-02-04 更新2026-04-28 收录

多模态对齐评估

模型鲁棒性分析

数据链接：

https://figshare.com/articles/dataset/_p_Multimodal_alignment_degradation_measured_by_CLIP_score_p_/31256008 数据链接链接失效反馈

官方服务：

资源简介：

Multimodal alignment degradation measured by CLIP score.

应用场景：

创建时间：

2026-02-04

跨域分类评估

模型鲁棒性分析

The top represents the classifier trained on photos, tested on paintings which is heavily biased towards satin. The bottom represents the classifier trained on paintings, tested on photos, which is mo

NIAID Data Ecosystem70

exp_inf_coeffvariation.py

统计实验评估

模型鲁棒性分析

Experiment entry point for the experiment in Section 4.2/Figure 1.

DataCite Commons2024-11-11 更新20

llm-xray-lesion-scans

模型可解释性

模型鲁棒性分析

LLM Lesion X-Ray 数据集是一个已撤回的历史数据集，包含六个约1B参数的语言模型的层损伤扫描结果。该数据集由 Tetracta AI 使用单一预注册协议生成，仅包含测量数据（KL散度值），不包含模型权重。数据集的背景在于：传统基准测试只能评估模型的知识输出，而无法揭示模型内部结构；本数据集通过逐层损伤（剪枝或加噪）并测量输出分布变化，试图回答“模型是如何构建的”这一问题。数据内容包括

Hugging Face2026-09-06 更新10

LLM Benchmarking

大型语言模型评估

模型鲁棒性分析

data.zip: All the questions that used in the expirements saved for reproducibility reasons rephrased_data.zip: All the rephrased questions that used in the expirements saved for reproducibility reaso

Zenodo2025-05-14 更新30

Relationship between yield and robustness for four types of perturbation (linear models).

模型鲁棒性分析

线性模型评估

Relationship between yield and robustness for four types of perturbation (linear models).

Figshare2015-12-02 更新10