Related papers: LLM-Lasso: A Robust Framework for Domain-Informed …

The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in…

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…

Large Language Models (LLMs) are increasingly integrated into critical decision-making pipelines, a trend that raises the demand for robust and automated data analysis. Current approaches to dataset risk analysis are limited to manual…

The performance of machine learning models on tabular data is critically dependent on high-quality feature engineering. While Large Language Models (LLMs) have shown promise in automating feature extraction (AutoFE), existing methods are…

Long-context modeling has drawn more and more attention in the area of Large Language Models (LLMs). Continual training with long-context data becomes the de-facto method to equip LLMs with the ability to process long inputs. However, it…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

The development of Large Speech-Language Models (LSLMs) has been slowed by fragmented architectures and a lack of transparency, hindering the systematic comparison and reproducibility of research. Unlike in the vision-language domain, the…

In legal matters, text classification models are most often used to filter through large datasets in search of documents that meet certain pre-selected criteria like relevance to a certain subject matter, such as legally privileged…

Algorithm selection, a critical process of automated machine learning, aims to identify the most suitable algorithm for solving a specific problem prior to execution. Mainstream algorithm selection techniques heavily rely on problem…

This paper presents a novel methodological framework for detecting and classifying latent constructs, including frames, narratives, and topics, from textual data using Open-Source Large Language Models (LLMs). The proposed hybrid approach…

Regularized regression approaches such as the Lasso have been widely adopted for constructing sparse linear models in high-dimensional datasets. A complexity in fitting these models is the tuning of the parameters which control the level of…

Active learning (AL) accelerates scientific discovery by prioritizing the most informative experiments, but traditional machine learning (ML) models used in AL suffer from cold-start limitations and domain-specific feature engineering,…

High-quality training data is critical to the performance of large language models (LLMs). Recent work has explored using LLMs to rate and select data based on a small set of human-designed criteria (rules), but these approaches often rely…

Few-shot semantic segmentation (FSS) aims to enable models to segment novel/unseen object classes using only a limited number of labeled examples. However, current FSS methods frequently struggle with generalization due to incomplete and…

Large language models (LLMs) have transformed human writing by enhancing grammar correction, content expansion, and stylistic refinement. However, their widespread use raises concerns about authorship, originality, and ethics, even…

Penalization schemes like Lasso or ridge regression are routinely used to regress a response of interest on a high-dimensional set of potential predictors. Despite being decisive, the question of the relative strength of penalization is…

We propose a statistical framework built on latent variable modeling for scaling laws of large language models (LLMs). Our work is motivated by the rapid emergence of numerous new LLM families with distinct architectures and training…

Adapting Large Language Models in complex technical service domains is constrained by the absence of explicit cognitive chains in human demonstrations and the inherent ambiguity arising from the diversity of valid responses. These…

Large Language Model (LLM)-based agents have demonstrated remarkable success in solving complex tasks across a wide range of general-purpose applications. However, their performance often degrades in context-specific scenarios, such as…

We introduce context augmentation, a data-augmentation approach that uses large language models (LLMs) to generate contexts around observed strings as a means of facilitating valid frequentist inference. These generated contexts serve to…