Robustness of learning from task instructions
Traditional supervised learning mostly works on individual tasks and requires training on a
large set of task-specific examples. This paradigm seriously hinders the development of task …
large set of task-specific examples. This paradigm seriously hinders the development of task …
How to handle different types of out-of-distribution scenarios in computational argumentation? A comprehensive and fine-grained field study
The advent of pre-trained Language Models (LMs) has markedly advanced natural
language processing, but their efficacy in out-of-distribution (OOD) scenarios remains a …
language processing, but their efficacy in out-of-distribution (OOD) scenarios remains a …
Automated scoring of constructed response items in math assessment using large language models
Recent developments in the field of artificial intelligence allow for improved performance in
the automated assessment of extended response items in mathematics, potentially allowing …
the automated assessment of extended response items in mathematics, potentially allowing …
Robust Testing of AI Language Model Resiliency with Novel Adversarial Prompts
B Hannon, Y Kumar, D Gayle, JJ Li, P Morreale - Electronics, 2024 - mdpi.com
In the rapidly advancing field of Artificial Intelligence (AI), this study presents a critical
evaluation of the resilience and cybersecurity efficacy of leading AI models, including …
evaluation of the resilience and cybersecurity efficacy of leading AI models, including …
On measurement validity and language models: Increasing validity and decreasing bias with instructions
Language models like BERT or GPT are becoming increasingly popular measurement tools,
but are the measurements they produce valid? Literature suggests that there is still a …
but are the measurements they produce valid? Literature suggests that there is still a …
Building Efficient Universal Classifiers with Natural Language Inference
Generative Large Language Models (LLMs) have become the mainstream choice for
fewshot and zeroshot learning thanks to the universality of text generation. Many users …
fewshot and zeroshot learning thanks to the universality of text generation. Many users …
Collaboration between intelligent agents and large language models: A novel approach for enhancing code generation capability
X Bai, S Huang, C Wei, R Wang - Expert Systems with Applications, 2025 - Elsevier
Abstract Pre-trained Large Language Models (LLMs) have demonstrated significant
potential in the Natural Language to Code (NL2Code) task. However, user-provided natural …
potential in the Natural Language to Code (NL2Code) task. However, user-provided natural …
PROTECT: Parameter-Efficient Tuning for Few-Shot Robust Chinese Text Correction
Non-normative texts and euphemisms are widely spread on the Internet, making it more
difficult to moderate the content. These phenomena result from misspelling errors or …
difficult to moderate the content. These phenomena result from misspelling errors or …
Rethinking ChatGPT's Success: Usability and Cognitive Behaviors Enabled by Auto-regressive LLMs' Prompting
X Li, M Liu - arXiv preprint arXiv:2405.10474, 2024 - arxiv.org
Over the last decade, a wide range of training and deployment strategies for Large
Language Models (LLMs) have emerged. Among these, the prompting paradigms of Auto …
Language Models (LLMs) have emerged. Among these, the prompting paradigms of Auto …
Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUs
This paper presents a SYCL implementation of Multi-Layer Perceptrons (MLPs), which
targets and is optimized for the Intel Data Center GPU Max 1550. To increase the …
targets and is optimized for the Intel Data Center GPU Max 1550. To increase the …