{"id":124,"date":"2023-04-24T12:47:00","date_gmt":"2023-04-24T03:47:00","guid":{"rendered":"https:\/\/datalab.flitto.com\/en\/company\/blog\/?p=124"},"modified":"2023-11-15T20:04:15","modified_gmt":"2023-11-15T11:04:15","slug":"generative-ai-applications-creativity-vs-accuracy","status":"publish","type":"post","link":"https:\/\/datalab.flitto.com\/en\/company\/blog\/generative-ai-applications-creativity-vs-accuracy\/","title":{"rendered":"Generative AI applications: Creativity vs. accuracy"},"content":{"rendered":"\n

<\/a><\/p>\n\n\n\n

Large language models (LLMs) are not a new concept. Numerous tech companies have been developing their own LLMs even before the superficial success of ChatGPT and other generative AI applications. Over years, the neural giants saw remarkable advancements, especially when it comes to their mechanisms. Generative AI applications that utilize LLMs<\/a> also display stunning versatility today.<\/p>\n\n\n\n

Different LLMs each have distinct characteristics. While their compositions, performance, and sizes may vary when it comes to supported languages or data sizes, they have a common goal, which is to offer values to their end-users.<\/p>\n\n\n\n

Meanwhile, not a single LLM provides a one-for-all solution to all end-user needs. An ongoing problem for generative AIs available so far is their unreliability despite the seeming cleverness. <\/p>\n\n\n\n

If so, is it possible to achieve a foundational LLM that covers both accurate and creative generative AI applications? And how can we achieve it? <\/p>\n\n\n\n

<\/div>\n\n\n\n

First, what is a large language model?<\/h4>\n\n\n\n
<\/div>\n\n\n\n

A large language model (LLM) refers to a massive structure of language data that runs on a specific algorithm (model) that enables it to process, predict, and generate text. Each company has its own unique recipes to their own model.<\/p>\n\n\n\n

The number of parameters are often used to define the performance of LLMs. The parameter refers to the value in which the model can diversify its output and process inputs more efficiently. The amount of parameters is considered to be proportional to the size of the text data LLMs are trained on. The bigger the text dataset, the higher the parameters the models are able to process.<\/p>\n\n\n\n

Some LLMs, in order to scale these parameters to train on, utilize massive information as their initial unsupervised training dataset. For instance, these datasets could have been scraped from the internet<\/a>. LLMs trained this way can produce human-like output solely by the sheer amount of human-generated text they’ve learned.<\/p>\n\n\n\n

<\/div>\n\n\n\n

Bigger LLMs are not synonymous to better LLMs<\/h4>\n\n\n\n
<\/div>\n\n\n
\n
\"\"\/
Visual representation of generative models. Image courtesy of ODSC \u2014 Open Data Science\u2019s Medium blog<\/a><\/em><\/figcaption><\/figure>\n<\/div>\n\n\n
<\/div>\n\n\n\n

Not all information available in the world wide web is factual or informative. As goes the popular saying in the field of machine learning, \u201cgarbage in, garbage out,<\/em>\u201d the above-mentioned training method is in part what also limits the model. The resulting model is also left with parameters that contain biased, harmful, or completely wrong information that can be detrimental to the end-user experiences.<\/p>\n\n\n\n

To counter this, LLMs can be modified and trained for specific use cases through fine-tuning. The popularized ChatGPT is one such example. It was trained with a supervised fine-tuning method called Reinforcement Learning from Human Feedback<\/a>, or RLHF. This process involves human teachers who assess, score, and correct the model so that it can answer better next time. <\/p>\n\n\n\n

However, fine-tuning is a relatively superficial procedure. It’s another question whether it can completely block out unhelpful answers rooted in the foundational composition of the model.<\/p>\n\n\n\n

<\/div>\n\n\n\n

Use cases for \u201ccreative\u201d text generation via LLMs<\/h4>\n\n\n\n
<\/div>\n\n\n\n

One of the biggest assets for LLMs trained on massive text datasets is their capacity to produce natural results. These LLMs can be used to build “creative” generative AI tools that end-users can utilize for broad domains that do not require much fact-checking.<\/p>\n\n\n\n

Some of possible generative AI applications via these massive and creative LLMs include:<\/p>\n\n\n\n

<\/div>\n\n\n\n