Connecting large language models with evolutionary algorithms yields powerful prompt optimizers

Q Guo, R Wang, J Guo, B Li, K Song, X Tan… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models (LLMs) excel in various tasks, but they rely on carefully crafted
prompts that often demand substantial human effort. To automate this process, in this paper …

Alleviating hallucinations of large language models through induced hallucinations

Y Zhang, L Cui, W Bi, S Shi - arXiv preprint arXiv:2312.15710, 2023 - arxiv.org
Despite their impressive capabilities, large language models (LLMs) have been observed to
generate responses that include inaccurate or fabricated information, a phenomenon …

Large language models: a primer and gastroenterology applications

O Shahab, B El Kurdi, A Shaukat… - Therapeutic …, 2024 - journals.sagepub.com
Over the past year, the emergence of state-of-the-art large language models (LLMs) in tools
like ChatGPT has ushered in a rapid acceleration in artificial intelligence (AI) innovation …

Improving grammatical error correction with multimodal feature integration

T Fang, J Hu, DF Wong, X Wan, LS Chao… - Findings of the …, 2023 - aclanthology.org
Grammatical error correction (GEC) is a promising task aimed at correcting errors in a text.
Many methods have been proposed to facilitate this task with remarkable results. However …

Explore-instruct: Enhancing domain-specific instruction coverage through active exploration

F Wan, X Huang, T Yang, X Quan, W Bi… - arXiv preprint arXiv …, 2023 - arxiv.org
Instruction-tuning can be substantially optimized through enhanced diversity, resulting in
models capable of handling a broader spectrum of tasks. However, existing data employed …

Old moats for new models: Openness, control, and competition in generative ai

P Azoulay, JL Krieger, A Nagaraj - 2024 - nber.org
Drawing insights from the field of innovation economics, we discuss the likely competitive
environment shaping generative AI advances. Central to our analysis are the concepts of …

Unveiling the generalization power of fine-tuned large language models

H Yang, Y Zhang, J Xu, H Lu, PA Heng… - arXiv preprint arXiv …, 2024 - arxiv.org
While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities,
fine-tuning these models on downstream, domain-specific datasets is often necessary to …

Query performance prediction using relevance judgments generated by large language models

C Meng, N Arabzadeh, A Askari, M Aliannejadi… - arXiv preprint arXiv …, 2024 - arxiv.org
Query performance prediction (QPP) aims to estimate the retrieval quality of a search system
for a query without human relevance judgments. Previous QPP methods typically return a …

NaSGEC: a multi-domain Chinese grammatical error correction dataset from native speaker texts

Y Zhang, B Zhang, H Jiang, Z Li, C Li, F Huang… - arXiv preprint arXiv …, 2023 - arxiv.org
We introduce NaSGEC, a new dataset to facilitate research on Chinese grammatical error
correction (CGEC) for native speaker texts from multiple domains. Previous CGEC research …

RobustGEC: Robust Grammatical Error Correction Against Subtle Context Perturbation

Y Zhang, L Cui, E Zhao, W Bi, S Shi - arXiv preprint arXiv:2310.07299, 2023 - arxiv.org
Grammatical Error Correction (GEC) systems play a vital role in assisting people with their
daily writing tasks. However, users may sometimes come across a GEC system that initially …