探究大语言模型嵌入空间能否复现专家知识结构，为理解模型内部表示提供前沿视角
arXiv:2606.23394v1 Announce Type: new Abstract: Pretrained text embeddings are increasingly used as representational maps, yet high category separabil…
用贝叶斯层次模型结合嵌入空间聚类，从根源上修正LLM基准测试的提示敏感性，让模型评估更公平可靠。
arXiv:2510.05709v2 Announce Type: replace-cross Abstract: LLM benchmarking metrics often misstate performance and uncertainty as they rely on two assu…
生物多模态大模型合并新方法，利用嵌入空间信号实现跨模态融合，推动科学发现。
arXiv:2603.14405v2 Announce Type: replace Abstract: Biological multimodal large language models (MLLMs) have emerged as powerful foundation models for…
用扩散模型在嵌入空间生成环境声音特征，实现零样本分类新思路，精度提升显著。
arXiv:2412.03771v3 Announce Type: replace-cross Abstract: Zero-shot learning enables models to generalise to unseen classes by leveraging semantic inf…