Related papers: Synatra: Turning Indirect Knowledge into Direct De…

Adapting large language models (LLMs) to specific domains often faces a critical bottleneck: the scarcity of high-quality, human-curated data. While large volumes of unchecked data are readily available, indiscriminately using them for…

How can "weak teacher models" such as average human annotators or existing AI systems, effectively supervise LLMs to improve performance on hard reasoning tasks, especially those that challenge and requires expertise or daily practice from…

Synthetic training data generation with Large Language Models (LLMs) like Google's Gemma and OpenAI's GPT offer a promising solution to the challenge of obtaining large, labeled datasets for training classifiers. When rapid model deployment…

Access to real-world medical data is often restricted due to privacy regulations, posing a significant barrier to the advancement of healthcare research. Synthetic data offers a promising alternative; however, generating realistic,…

There is increasing interest in distilling task-specific knowledge from large language models (LLM) to smaller student models. Nonetheless, LLM distillation presents a dual challenge: 1) there is a high cost associated with querying the…

The rapid growth of research output in control engineering calls for new approaches to structure and formalize domain knowledge. This paper briefly describes an LLM-supported method for semi-automated generation of formal knowledge…

Automating the decision of whether a code change requires manual review is vital for maintaining software quality in modern development workflows. However, the emergence of new programming languages and frameworks creates a critical…

In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges when deployed in novel environments or required to navigate…

Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data. To make the resulting model useful to users,…

Reinforcement Learning (RL) has been shown to significantly boost reasoning capabilities of large language models (LLMs) in math, coding, and multi-hop reasoning tasks. However, RL fine-tuning requires abundant high-quality verifiable data,…

HRA (Human Reliability Analysis) data is crucial for advancing HRA methodologies. however, existing data collection methods lack the necessary granularity, and most approaches fail to capture dynamic features. Additionally, many methods…

A growing number of approaches exist to generate explanations for image classification. However, few of these approaches are subjected to human-subject evaluations, partly because it is challenging to design controlled experiments with…

Understanding data visualizations like charts and plots requires reasoning about both visual elements and numerics. Although strong in extractive questions, current chart visual question answering (chart VQA) models suffer on complex…

Learning from Demonstration (LfD) is a framework that allows lay users to easily program robots. However, the efficiency of robot learning and the robot's ability to generalize to task variations hinges upon the quality and quantity of the…

Traditional code instruction data synthesis methods suffer from limited diversity and poor logic. We introduce Infinite-Instruct, an automated framework for synthesizing high-quality question-answer pairs, designed to enhance the code…

Faced with an expensive human annotation process, creators of NLP systems increasingly turn to synthetic data generation. While this method shows promise, the extent to which synthetic data can replace human annotation is poorly understood.…

Reinforcement learning (RL) makes it possible to train agents capable of achieving sophisticated goals in complex and uncertain environments. A key difficulty in reinforcement learning is specifying a reward function for the agent to…

AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot provide. Distributed systems are a prime example: properties…

Artificial intelligence (AI), machine learning, and deep learning (DL) methods are becoming increasingly important in the field of biomedical image analysis. However, to exploit the full potential of such methods, a representative number of…

Inventory management remains a challenge for many small and medium-sized businesses that lack the expertise to deploy advanced optimization methods. This paper investigates whether Large Language Models (LLMs) can help bridge this gap. We…