arXiv:2602. 02726v2 Announce Type: replace Abstract: Large language models (LLMs) encode rich semantic information in their hidden states, yet it remains difficult to understand what information these internal representations capture.
arXiv:2506. 20040v3 Announce Type: replace-cross Abstract: Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across adjacent layers, causing single-layer analyses to miss this cross-layer structure.
The paper examines whether Deep Embedded Clustering (DEC) truly overcomes the fundamental limitations of k‑means clustering, such as handling clusters of arbitrary shapes, varied sizes, and densities. Through analysis, it finds that DEC does not exploit the underlying data distribution and therefore fails to address these limitations. Instead, a non‑deep learning approach that leverages distributional information of clusters can achieve the intended goals of deep clustering.
arXiv:2607. 04548v1 Announce Type: cross Abstract: Novel category discovery aims to identify unseen classes from unlabeled data by transferring knowledge from labeled categories, but most existing methods perform discovery in opaque latent feature spaces.
arXiv:2512. 10092v2 Announce Type: replace Abstract: Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data.
arXiv:2505.10202v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their e...
arXiv:2510. 09711v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches.
arXiv:2608. 07881v1 Announce Type: new Abstract: Clustering mixed tabular data requires a unified metric space to bridge the inherent heterogeneity between continuous numerical measurements and discrete categorical symbols.
arXiv:2607. 00620v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) aims to recognize known classes while autonomously discovering novel ones in open-world settings.
arXiv:2512. 07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.
arXiv:2507.22920v2 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has intensified the need for effective mechanisms to transform continuous multimodal data int...
arXiv:2606. 19489v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) enhance interpretability by projecting learned features into a human-understandable concept space.
arXiv:2509. 25045v3 Announce Type: replace-cross Abstract: Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations.