The rise of Large Language Models (LLMs) has revolutionized numerous domains, yet these models still exhibit weakness in understanding structured tabular data. Although the growing context window promises to accommodate a larger volume of table contents, it does not inherently improve the model's ability to understand the underlying structure and semantics of tabular data. To bridge the semantic gap between **T**ext and **T**able, we propose **T**n**T**, a table-language model that features multimodal table representations to empower LLMs to effectively and efficiently abstract structure-enriched semantics from tabular data. **T**n**T** also introduces a scalable and efficient training pipeline, featuring novel self-supervised tasks, to integrate abstract tabular knowledge into the language modality. Extensive experimental results on NL2SQL demonstrate a much better table understanding of **T**n**T**, which achieves up to **14.4** higher execution accuracy compared with traditional text-based table representations.

Positive-Unlabeled (PU) learning aims to train a binary classifier using minimal positive data supplemented by a substantially larger pool of unlabeled data, in the specific absence of explicitly annotated negatives. Despite its straightforward nature as a binary classification task, the currently best-performing PU algorithms still largely lag behind the supervised counterpart. In this work, we identify that the primary bottleneck lies in the difficulty of deriving discriminative representations under unreliable binary supervision with poor semantics, which subsequently hinders the common label disambiguation procedures. To cope with this problem, we propose a novel PU learning framework, namely Latent Group-Aware Meta Dis-ambiguation (LaGAM), which incorporates a hierarchical contrastive learning module to extract the underlying grouping semantics within PU data and produce compact representations. As a result, LaGAM enables a more aggressive label disambiguation strategy, where we enhance the robustness of training by iteratively distilling the true labels of unlabeled data directly through meta-learning. Extensive experiments show that LaGAM significantly outperforms the current state-of-the-art methods by an average of 6.8% accuracy on common benchmarks, approaching the supervised baseline. We also provide comprehensive ablations as well as visualized analysis to verify the effectiveness of our LaGam. The code is available at https://github.com/llong-cs/LaGAM.

In the era of big data, data annotation is integral to numerous applications. However, it is widely acknowledged as a laborious and time-consuming process, significantly impeding the scalability and efficiency of data-driven applications. To reduce the human cost, we demonstrate CORAL, a collaborative automatic labeling system driven by large language models (LLMs), which achieves high-quality annotation with the least human effort. Firstly, CORAL employs LLM to automatically annotate vast datasets, generating coarse-grained labels. Subsequently, a weakly-supervised learning module trains small language models (SLMs) using noisy label learning techniques to distill accurate labels from LLM's annotations. It also allows statistical analysis of model outcomes to identify potentially erroneous labels, reducing the human cost of error detection. Furthermore, CORAL supports iterative refinement by LLMs and SLMs using manually corrected labels, thereby ensuring continual enhancement in annotation quality and model performance. A visual interface enables annotation process monitoring and result analysis.