Rabota.ru has developed an AI-based service that can write job descriptions. The company implemented a Sammarization model trained using RLHF (Human Preference Reinforcement Learning).
As noted on Rabota.ru, the technology allows you to write short job descriptions that are immediately displayed in search results without revealing the full text. The new development is capable of composing large informative texts of no more than 200 characters. This is the description that the applicant will see when searching for vacancies on the main page of the service.
To train the neural network, the specialists generated thousands of job descriptions for various job openings and manually ranked them by quality. Next, we train an auxiliary reward model for the classification task. And with their help, the neural network was trained to generate only acceptable short descriptions.
“For training and work, an internal cluster containing NVIDIA Tesla video cards is used. After the introduction of the new ML model, we received an average daily increase of 16,000 additional visits and around 1,000 additional responses,” the service explained.
Previously, RTU MIREA urged the Ministry of Digital Transformation to introduce mandatory labeling of content created through neural networks.
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.