LLM CLASSIFIER: MESSAGE VALIDATION ON PROFANITY
DOI:
https://doi.org/10.17770/het2024.28.8262Keywords:
Dataset, ChatGPT 3.5, Cohera, LLMAbstract
The aim of the given scientific paper "Message validation on profanity using LLM” to train LLM to detect profanity in user messages. During the research, the authors created a dataset of 30 phrases (15 good, 15 bad), which were then used to train LLM using AI platform Cohera and evaluated the recognition accuracy. The authors achieved accuracy equal to 70%.
Downloads
References
What Is A Large Language Model (LLM)? A Complete Guide. [tiešsaiste 22.03.2024.]. Pieejas veids: https://www.hostinger.com/tutorials/large-language-models?ppc_campaign=google_search_generic_hosting_all&bidkw=defaultkeyword&lo=9075644&gad_source=1&gclid=Cj0KCQjw2PSvBhDjARIsAKc2cgOQyPS0JVEpWalFc4hcqEho1QYLmIAnPmBDpN7lzdDJlTpfP6A3bLsaAok5EALw_wcB
Attention Is All You Need. [tiešsaiste 08.04.2024.]. Pieejams: 1706.03762.pdf (arxiv.org)
Best Large Language Models for 2024 and How to Choose the Right One for Your Site. [tieššaiste 22.03.2024.]. Pieejas veids: https://www.hostinger.com/tutorials/large-language-models?ppc_campaign=google_search_generic_hosting_all&bidkw=defaultkeyword&lo=9075644&gad_source=1&gclid=Cj0KCQjw2PSvBhDjARIsAKc2cgOQyPS0JVEpWalFc4hcqEho1QYLmIAnPmBDpN7lzdDJlTpfP6A3bLsaAok5EALw_wcB#1_GPT_35
Datu kopa ChatGPT3.5 [tiešsaiste 22.03.2024.].Pieejas veids: https://chat.openai.com/
Make database. [tiešsaiste 03.04.2024.]. Pieejams: https://chat.openai.com/auth/login?next=%2Fc%2F1444a459-dfb0-4b8d-b378-b2aece7c6413
Introduction to Large Language Models. [tiešsaiste 29.03.2024.]. Pieejams: https://docs.cohere.com/docs/introduction-to-large-language-models
LLMs – Model Architectures and Pre-Training Objectives. [tiešsaiste 11.04.2024.]. Pieejams: https://ritikjain51.medium.com/llms-model-architectures-and-pre-training-objectives-39c4543edef0
