Related papers: Capturing LLM Capabilities via Evidence-Calibrated…

Effective representation of data is crucial in various machine learning tasks, as it captures the underlying structure and context of the data. Embeddings have emerged as a powerful technique for data representation, but evaluating their…

Large language models (LLMs) have shown great potential in natural language processing and content generation. However, current LLMs heavily rely on cloud computing, leading to prolonged latency, high bandwidth cost, and privacy concerns.…

For speech classification tasks, deep learning models often achieve high accuracy but exhibit shortcomings in calibration, manifesting as classifiers exhibiting overconfidence. The significance of calibration lies in its critical role in…

Ontology, and more broadly, Knowledge Graph Matching is a challenging task in which expressiveness has not been fully addressed. Despite the increasing use of embeddings and language models for this task, approaches for generating…

We introduce ClusterLLM, a novel text clustering framework that leverages feedback from an instruction-tuned large language model, such as ChatGPT. Compared with traditional unsupervised methods that builds upon "small" embedders,…

The rapidly growing ecosystem of Large Language Models (LLMs) makes it increasingly challenging to manage and utilize the vast and dynamic pool of models effectively. We propose LOCUS, a method that produces low-dimensional vector…

Multi-label classification is a type of supervised machine learning that can simultaneously assign multiple labels to an instance. To solve this task, some methods divide the original problem into several sub-problems (local approach),…

Unsupervised methods are widely used to induce latent semantic structure from large text collections, yet their outputs often contain incoherent, redundant, or poorly grounded clusters that are difficult to validate without labeled data. We…

We introduce LM-Lexicon, an innovative definition modeling approach that incorporates data clustering, semantic expert learning, and model merging using a sparse mixture-of-experts architecture. By decomposing the definition modeling task…

Cloud-device collaborative recommendation partitions computation across the cloud and user devices: the cloud provides semantic user modeling, while the device leverages recent interactions and cloud semantic signals for privacy-preserving,…

Embodied AI has made significant progress acting in unexplored environments. However, tasks such as object search have largely focused on efficient policy learning. In this work, we identify several gaps in current search methods: They…

Concept bottleneck models (CBMs) have emerged as critical tools in domains where interpretability is paramount. These models rely on predefined textual descriptions, referred to as concepts, to inform their decision-making process and offer…

Our work addresses the challenges of understanding tables. Existing methods often struggle with the unpredictable nature of table content, leading to a reliance on preprocessing and keyword matching. They also face limitations due to the…

Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack…

While several feature embedding models have been developed in the literature, comparisons of these embeddings have largely focused on their numerical performance in classification-related downstream applications. However, an interpretable…

Cross-lingual word embeddings (CLEs) enable multilingual modeling of meaning and facilitate cross-lingual transfer of NLP models. Despite their ubiquitous usage in downstream tasks, recent increasingly popular projection-based CLE models…

The high dimensional and semantically complex nature of textual Big data presents significant challenges for text clustering, which frequently lead to suboptimal groupings when using conventional techniques like k-means or hierarchical…

In-context learning enables language models (LM) to adapt to downstream data or tasks by incorporating few samples as demonstrations within the prompts. It offers strong performance without the expense of fine-tuning. However, the…

Embeddings are a powerful way to enrich data-driven machine learning models with the world knowledge of large language models (LLMs). Yet, there is limited evidence on how to design effective LLM-based embedding pipelines for tabular…

Educators evaluate student knowledge using knowledge component (KC) models that map assessment questions to KCs. Still, designing KC models for large question banks remains an insurmountable challenge for instructors who need to analyze…