LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models

Autor: Elesedy, Hayder, Esperança, Pedro M., Oprea, Silviu Vlad, Ozay, Mete

Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for resource-constrained computational portable devices, such as mobile phone

Externí odkaz: http://arxiv.org/abs/2407.02987

Effect of Probiotic Therapy on Neuropsychiatric Manifestations in Children with Multiple Neurotransmitter Disorders: A Study

Autor: Loredana Matiș, Bogdana Ariana Alexandru, Radu Fodor, Lucia Georgeta Daina, Timea Claudia Ghitea, Silviu Vlad

Publikováno v: Biomedicines, Vol 11, Iss 10, p 2643 (2023)

Probiotics, also known as psychobiotics, have been linked to cognitive functions, memory, learning, and behavior, in addition to their positive effects on the digestive tract. The purpose of this study is to examine the psychoemotional effects and co

Externí odkaz: https://doaj.org/article/a159a06017eb4efa834c2e6949b8c358

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Sarcasm Detection is Way Too Easy! An Empirical Comparison of Human and Machine Sarcasm Detection

Autor: Abu Farha, Ibrahim, Wilson, Steven, Oprea, Silviu Vlad, Magdy, Walid

Publikováno v: Abu Farha, I, Wilson, S, Oprea, S V & Magdy, W 2023, Sarcasm Detection is Way Too Easy! An Empirical Comparison of Human and Machine Sarcasm Detection . in Y Goldberg, Z Kozareva & Y Zhang (eds), Findings of the Association for Computational Linguistics: EMNLP 2022 . Abu Dhabi, pp. 5284–5295, The 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates, 7/12/22 . < https://aclanthology.org/2022.findings-emnlp.387/ >

Recently, author-annotated sarcasm datasets, which focus on intended, rather than perceived sarcasm, have been introduced. Although datasets collected using first-party annotation have important benefits, there is no comparison of human and machine p

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3094::22ea1d5e48fb9bc87b5906de5ca841ec
https://hdl.handle.net/20.500.11820/dc22eb7f-a486-42ac-b51f-18b2dbe96355

Should a Chatbot be Sarcastic? Understanding User Preferences Towards Sarcasm Generation

Autor: Silviu Vlad Oprea, Steven Wilson, Walid Magdy

Publikováno v: Oprea, S V, Wilson, S & Magdy, W 2022, Should a Chatbot be Sarcastic? Understanding User Preferences Towards Sarcasm Generation . in S Muresan, P Nakov & A Villavicencio (eds), Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) : Proceedings of the Conference, Vol. 1 (Long Papers) . vol. 1, pp. 7686-7700, 60th Annual Meeting of the Association for Computational Linguistics, Dublin, Ireland, 22/05/22 . < https://aclanthology.org/2022.acl-long.530 >

Previous sarcasm generation research has focused on how to generate text that people perceive as sarcastic to create more human-like interactions. In this paper, we argue that we should first turn our attention to the question of when sarcasm should

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e3cb85ab9dd7d64f589abcd6fc4c419
https://hdl.handle.net/20.500.11820/7aa2f011-5c01-4290-aec0-0e9e433bc051