Related papers: Dataset Featurization: Uncovering Natural Language…
Feature engineering for tabular data remains a critical yet challenging step in machine learning. Recently, large language models (LLMs) have been used to automatically generate new features by leveraging their vast knowledge. However,…
The representation of feature space is a crucial environment where data points get vectorized and embedded for subsequent modeling. Thus the efficacy of machine learning (ML) algorithms is closely related to the quality of feature…
Feature transformation aims to reconstruct the feature space of raw features to enhance the performance of downstream models. However, the exponential growth in the combinations of features and operations poses a challenge, making it…
Detecting jailbreak attempts in clinical training large language models (LLMs) requires accurate modeling of linguistic deviations that signal unsafe or off-task user behavior. Prior work on the 2-Sigma clinical simulation platform showed…
This paper explores the application of large language models (LLMs) to extract nuanced and complex job features from unstructured job postings. Using a dataset of 1.2 million job postings provided by AdeptID, we developed a robust pipeline…
We introduce LLM-Lasso, a novel framework that leverages large language models (LLMs) to guide feature selection in Lasso $\ell_1$ regression. Unlike traditional methods that rely solely on numerical data, LLM-Lasso incorporates…
Social media user profiling through content analysis is crucial for tasks like misinformation detection, engagement prediction, hate speech monitoring, and user behavior modeling. However, existing profiling techniques, including tweet…
Change detection is a fundamental task in computer vision that processes a bi-temporal image pair to differentiate between semantically altered and unaltered regions. Large language models (LLMs) have been utilized in various domains for…
The rapid advancement of Large Language Models (LLMs) has significantly influenced various domains, leveraging their exceptional few-shot and zero-shot learning capabilities. In this work, we aim to explore and understand the LLMs-based…
Large Language Models (LLMs), with their remarkable ability to tackle challenging and unseen reasoning problems, hold immense potential for tabular learning, that is vital for many real-world applications. In this paper, we propose a novel…
This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs). Our two-step approach involves data point…
Data selection for fine-tuning large language models (LLMs) aims to choose a high-quality subset from existing datasets, allowing the trained model to outperform baselines trained on the full dataset. However, the expanding body of research…
Tracking how data is mentioned and used in research papers provides critical insights for improving data discoverability, quality, and production. However, manually identifying and classifying dataset mentions across vast academic…
Large Language Models (LLMs) often generate responses that are factually incorrect yet expressed with high confidence, which can pose serious risks for end users. To address this, it is essential for LLMs not only to produce answers but…
Recent regulatory initiatives like the European AI Act and relevant voices in the Machine Learning (ML) community stress the need to describe datasets along several key dimensions for trustworthy AI, such as the provenance processes and…
Despite the impressive capabilities of large language models (LLMs), their performance on information extraction tasks is still not entirely satisfactory. However, their remarkable rewriting capabilities and extensive world knowledge offer…
Making sense of unstructured text datasets is perennially difficult, yet increasingly relevant with Large Language Models. Data workers often rely on dataset summaries, especially distributions of various derived features. Some features,…
Large language models (LLMs) have demonstrated remarkable potential across a broad range of applications. However, producing reliable text that faithfully represents data remains a challenge. While prior work has shown that task-specific…
The increasing capacities of large language models (LLMs) have been shown to present an unprecedented opportunity to scale up data analytics in the humanities and social sciences, by automating complex qualitative tasks otherwise typically…
With the exponential increase in online scientific literature, identifying reliable domain-specific data has become increasingly important but also very challenging. Manual data collection and filtering for domain-specific scientific…