10 . Direction: Fill in each blank with a proper word chosen from the box. Each word can be used only once. Note that there is one word more than you need.
A. auto-complete B. determine C. essentially D. grammatical E. grouped
F. indicating G. instructions H. likely I. resembles J. rigidly
K. simple |
How do AI chatbots answer my questions
Chatbots might appear to be complex conversationalists that respond like real people. But if you take a closer look, they are 1 an advanced version of a program that finishes your sentences by predicting which words will come next. Bard, ChatGPT, and other AI technologies are large language models—a kind of algorithm (算法) trained on exercises similar to the Mad Libs-style questions found on elementary school quizzes. More simply put, they are human-written 2 that tell computers how to solve a problem or make a calculation. In this case, the algorithm uses your prompt and any sentences it comes across to 3 the answer.
Let’s pretend you plugged this sentence into an AI chatbot: “The cat sat on the ______.” First, the language model would have to know that the missing word needs to be a noun to make 4 sense. But it can’t be any noun—the cat can’t sit on the “democracy,” for one. So the algorithm searches texts written by humans to get a sense of what cats actually rest on and picks out the most probable answer. In this scenario, it might 5 the cat sits on the “laptop” 10 percent of the time, on the “table” 20 percent of the time, and on the “chair” 70 percent of the time. The model would then go with the most 6 answer: “chair.” The system is able to use this prediction process to respond with a full sentence. If you ask a chatbot, “How are you?” it will generate “I’m” based on the “you” from the question and then “good” based on what most people on the web reply when asked how they are.
The way these programs process information and arrive at a decision sort of 7 how the human brain behaves. “ 8 as this task—predicting the most probable response—is, it actually requires an incredibly advanced knowledge of both how language works and how the world works,” says Yoon Kim, a researcher at MIT’s Computer Science and Artificial Intelligence Laboratory.
The beauty of language models is that researchers don’t have to 9 define any rules or grammar for them to follow. An AI chatbot learns how to form sentences that make sense by consuming textual elements, which are common sequences of characters 10 together taken from the raw text of books, articles, and websites. All it needs are the patterns and associations it finds among certain words or phrases.
