The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic information. Indeed, it is natural to assume that these pre-trained representations do encode some level of linguistic knowledge as they have brought about large empirical improvements on a wide variety of NLP tasks, which suggests they are learning true linguistic generalization. In this work, we focus on intrinsic probing, an analysis technique where the goal is not only to identify whether a representation encodes a linguistic attribute but also to pinpoint where this attribute is encoded. We propose a novel latent-variable formulation for constructing intrinsic probes and derive a tractable variational approximation to the log-likelihood. Our results show that our model is versatile and yields tighter mutual information estimates than two intrinsic probes previously proposed in the literature. Finally, we find empirical evidence that pre-trained representations develop a cross-lingually entangled notion of morphosyntax.
Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation
School of Informatics, Xiamen University（厦门大学信息学院）；The Hong Kong Polytechnic University（香港理工大学）；University of Chinese Academy of Sciences（中国科学院大学）；Alibaba Group（阿里巴巴集团）；Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China（福建省和台湾非物质文化遗产数字化保护与智能处理重点实验室（厦门大学），中华人民共和国文化和旅游部，中国）
FlashMem: Distilling Intrinsic Latent Memory via Computation Reuse
School of ASEE, Beihang University（北京航空航天大学ASEE学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；School of BME, Beijing Advanced Innovation Center for BME, Beihang University（北京航空航天大学生物医学工程学院/北京生物医学工程高精尖创新中心）；CAIR and CECS, VinUniversity（VinUniversity计算与人工智能研究中心/计算机工程与计算机科学系）
Probing the Robustness of Large Language Models Safety to Latent Perturbations
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际 Graduate School, 清华大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Fudan University（复旦大学）；The University of Hong Kong（香港大学）
