A comprehensive survey of ai-generated content (aigc): A history of generative ai from gan to chatgpt

Y Cao, S Li, Y Liu, Z Yan, Y Dai, PS Yu… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Recently, ChatGPT, along with DALL-E-2 and Codex, has been gaining significant attention
from society. As a result, many individuals have become interested in related resources and …

How to prompt? Opportunities and challenges of zero-and few-shot learning for human-AI interaction in creative applications of generative models

H Dang, L Mecke, F Lehmann, S Goller… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Deep generative models have the potential to fundamentally change the way we create high-
fidelity digital content but are often hard to control. Prompting a generative model is a …

Lost in the middle: How language models use long contexts

NF Liu, K Lin, J Hewitt, A Paranjape… - Transactions of the …, 2024‏ - direct.mit.edu
While recent language models have the ability to take long contexts as input, relatively little
is known about how well they use longer context. We analyze the performance of language …

The power of noise: Redefining retrieval for rag systems

F Cuconasu, G Trappolini, F Siciliano, S Filice… - Proceedings of the 47th …, 2024‏ - dl.acm.org
Retrieval-Augmented Generation (RAG) has recently emerged as a method to extend
beyond the pre-trained knowledge of Large Language Models by augmenting the original …

Calibrate before use: Improving few-shot performance of language models

Z Zhao, E Wallace, S Feng, D Klein… - … on machine learning, 2021‏ - proceedings.mlr.press
GPT-3 can perform numerous tasks when provided a natural language prompt that contains
a few training examples. We show that this type of few-shot learning can be unstable: the …

Towards efficient generative large language model serving: A survey from algorithms to systems

X Miao, G Oliaro, Z Zhang, X Cheng, H **… - arxiv preprint arxiv …, 2023‏ - arxiv.org
In the rapidly evolving landscape of artificial intelligence (AI), generative large language
models (LLMs) stand at the forefront, revolutionizing how we interact with our data. However …

On the explainability of natural language processing deep models

JE Zini, M Awad - ACM Computing Surveys, 2022‏ - dl.acm.org
Despite their success, deep networks are used as black-box models with outputs that are not
easily explainable during the learning and the prediction phases. This lack of interpretability …

Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting

S Li, X **, Y Xuan, X Zhou, W Chen… - Advances in neural …, 2019‏ - proceedings.neurips.cc
Time series forecasting is an important problem across many domains, including predictions
of solar plant energy output, electricity consumption, and traffic jam situation. In this paper …

What does bert look at? an analysis of bert's attention

K Clark, U Khandelwal, O Levy, CD Manning - arxiv preprint arxiv …, 2019‏ - arxiv.org
Large pre-trained neural networks such as BERT have had great recent success in NLP,
motivating a growing body of research investigating what aspects of language they are able …

A survey on deep learning based knowledge tracing

X Song, J Li, T Cai, S Yang, T Yang, C Liu - Knowledge-Based Systems, 2022‏ - Elsevier
Abstract “Knowledge tracing (KT)” is an emerging and popular research topic in the field of
online education that seeks to assess students' mastery of a concept based on their …