Машиннное обучение | Наука о данных Библиотека | Telegram Webview: machinelearning_books/1026 -

Telegram Group & Telegram Channel

Машиннное обучение | Наука о данных Библиотека

📄 Это исследование оценивает 14 техник prompt-инжиниринга для 10 задач в области Software Engineering, используя 4 разных LLM.

Методология 🔧:

● Эффективность оценивалась с помощью метрик: Accuracy, F1 score, CodeBLEU, BLEU.

● Анализировались лингвистические характеристики prompt'ов: лексическое разнообразие, число токенов и их связь с качеством ответа.

● Применялась контрастивная интерпретация, чтобы выявить ключевые факторы, влияющие на результативность техник.

📌 Выводы помогут понять, какие типы prompt'ов реально работают в инженерных задачах и почему.

Читать

www.group-telegram.com/in/machinelearning_books.com/1025

1.7K viewsJun 10 at 09:00

group-telegram.com/machinelearning_books/1026

Create: 2025-06-10
Last Update: 2025-06-18 20:37:19

📄 Это исследование оценивает 14 техник prompt-инжиниринга для 10 задач в области Software Engineering, используя 4 разных LLM.

Методология 🔧:

● Эффективность оценивалась с помощью метрик: Accuracy, F1 score, CodeBLEU, BLEU.

● Анализировались лингвистические характеристики prompt'ов: лексическое разнообразие, число токенов и их связь с качеством ответа.

● Применялась контрастивная интерпретация, чтобы выявить ключевые факторы, влияющие на результативность техник.

📌 Выводы помогут понять, какие типы prompt'ов реально работают в инженерных задачах и почему.

Читать

BY Машиннное обучение | Наука о данных Библиотека

Share with your friend now:
group-telegram.com/machinelearning_books/1026

Open in Telegram

Telegram | DID YOU KNOW?

Date: 2025-06-18|

This ability to mix the public and the private, as well as the ability to use bots to engage with users has proved to be problematic. In early 2021, a database selling phone numbers pulled from Facebook was selling numbers for $20 per lookup. Similarly, security researchers found a network of deepfake bots on the platform that were generating images of people submitted by users to create non-consensual imagery, some of which involved children. The War on Fakes channel has repeatedly attempted to push conspiracies that footage from Ukraine is somehow being falsified. One post on the channel from February 24 claimed without evidence that a widely viewed photo of a Ukrainian woman injured in an airstrike in the city of Chuhuiv was doctored and that the woman was seen in a different photo days later without injuries. The post, which has over 600,000 views, also baselessly claimed that the woman's blood was actually makeup or grape juice. The next bit isn’t clear, but Durov reportedly claimed that his resignation, dated March 21st, was an April Fools’ prank. TechCrunch implies that it was a matter of principle, but it’s hard to be clear on the wheres, whos and whys. Similarly, on April 17th, the Moscow Times quoted Durov as saying that he quit the company after being pressured to reveal account details about Ukrainians protesting the then-president Viktor Yanukovych. For example, WhatsApp restricted the number of times a user could forward something, and developed automated systems that detect and flag objectionable content. Telegram does offer end-to-end encrypted communications through Secret Chats, but this is not the default setting. Standard conversations use the MTProto method, enabling server-client encryption but with them stored on the server for ease-of-access. This makes using Telegram across multiple devices simple, but also means that the regular Telegram chats you’re having with folks are not as secure as you may believe.
from in

Telegram Машиннное обучение | Наука о данных Библиотека
FROM American