Large language models (LLMs) are being increasingly incorporated into scientific workflows. However, we have yet to fully grasp the implications of this integration. How should the advent of large language models affect the practice of science? For t...
We explore the ability of large language models to solve and generate puzzles from the NPR Sunday Puzzle game show using PUZZLEQA, a dataset comprising 15 years of on-air puzzles. We evaluate four large language models using PUZZLEQA, in both multipl...
Notebooks for Large Language Models (LLMs) Specialization (⭐ 826)
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models (⭐ 17404)
Official code repo for the O'Reilly Book - "Hands-On Large Language Models" (⭐ 23261)
We propose the Data Contamination Quiz (DCQ), a simple and effective approach to detect data contamination in large language models (LLMs) and estimate the amount of it. Specifically, we frame data contamination detection as a series of multiple-choi...
Mixture of Experts (MoE) models have enabled the scaling of Large Language Models (LLMs) and Vision Language Models (VLMs) by achieving massive parameter counts while maintaining computational efficiency. However, MoEs introduce several inference-tim...
Recent advancements in Large Language Models (LLMs) have significantly influenced the landscape of language and speech research. Despite this progress, these models lack specific benchmarking against state-of-the-art (SOTA) models tailored to particu...
Large language models (LLMs) exhibit robust capabilities in text generation and comprehension, mimicking human behavior and exhibiting synthetic personalities. However, some LLMs have displayed offensive personality, propagating toxic discourse. Exis...
In this work, we explore the possibility of using synthetically generated data for video-based gesture recognition with large pre-trained models. We consider whether these models have sufficiently robust and expressive representation spaces to enable...
The study aims at critically discussing the advantages and disadvantages of using quantitative and qualitative approaches and methods for language testing and assessment research.
This study investigates the complexity of regulatory affairs in the medical device industry, a critical factor influencing market access and patient care. Through qualitative research, we sought expert insights to understand the factors contributing...
Large language models (LLMs) hold potential for innovative HCI research, including the creation of synthetic personae. However, their black-box nature and propensity for hallucinations pose challenges. To address these limitations, this position pape...
This app has adopted this privacy policy (“Privacy Policy”) to explain how This app collects, stores, and uses the information collected in connection with This app’s Services. BY INSTALLING, USING, REGISTERING TO OR OTHERWISE ACCESSING THE SERVICES, YOU AGREE…
AI-generated synthetic data allows to distill the general patterns of existing data, that can then be shared safely as granular-level representative, yet novel data samples within the original semantics. In this work we explore approaches of incorpor...
Over the past years, the ever-growing trend on data storage demand, more specifically for "cold" data (i.e. rarely accessed), has motivated research for alternative systems of data storage. Because of its biochemical characteristics, synthetic DNA mo...
Large language models, also known as LLMs, are very large deep learning models that are pre-trained on vast amounts of data. The underlying transformer is a set of neural networks that consist of an …
The rapid development of large language models (LLMs) has provided significant support and opportunities for the advancement of domain-specific LLMs. However, fine-tuning these large models using Intangible Cultural Heritage (ICH) data inevitably fac...
Large language models, also known as LLMs, are very large deep learning models that are pre-trained on vast amounts of data. The underlying transformer is a set of neural networks that consist of an â¦
Knowledge infusion is a promising method for enhancing Large Language Models for domain-specific NLP tasks rather than pre-training models over large data from scratch. These augmented LLMs typically depend on additional pre-training or knowledge pro...