# few-shot-learning

Published articles for few-shot-learning.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Собственный контент-фильтр на базе LLM: от эксперимента до стабильной системы

DevFeed: [Собственный контент-фильтр на базе LLM: от эксперимента до стабильной системы](<https://devfeed.tech/articles/llm-24021.md>)

Original publisher: [Read original article](<https://habr.com/ru/companies/redmadrobot/articles/922680/>)

Author: Martianov (red\_mad\_robot)

Published: 2025-06-27T15:23:17Z

Content type: tutorial

Language: ru

Sources: [Redmadrobot EN](<https://devfeed.tech/sources/redmadrobot-en.md>), [Redmadrobot RU](<https://devfeed.tech/sources/redmadrobot-ru.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [llama](<https://devfeed.tech/topics/llama.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [false-positive](<https://devfeed.tech/tags/false-positive.md>), [few-shot](<https://devfeed.tech/tags/few-shot.md>), [few-shot-learning](<https://devfeed.tech/tags/few-shot-learning.md>), [filter](<https://devfeed.tech/tags/filter.md>), [llama](<https://devfeed.tech/tags/llama.md>), [llm](<https://devfeed.tech/tags/llm.md>), [tag-6faff4be08e9](<https://devfeed.tech/tags/tag-6faff4be08e9.md>), [tag-b6293b9d443d](<https://devfeed.tech/tags/tag-b6293b9d443d.md>)

### AI overview

The article describes how red_mad_robot developed a proprietary LLM-based content filter for AI services. It explains why heuristic methods such as regular expressions and keyword filters produced false positives and were easy to bypass, and outlines the use of real anonymized user queries and a structured model prompt to improve moderation.

### Source excerpt

Привет! Меня зовут Миша Мартьянов, я инженер по исследованиям и разработке в red_mad_robot. Моя работа -- искать новые идеи, проверять гипотезы и улучшать продукты. На этом пути иногда приходится изобретать уникальные решения. Например, мы создали собственный фильтр, чтобы отсеивать нежелательный контент с помощью LLM. Рассказываю, как мы к этому пришли и с какими сложностями столкнулись. Читать далее

## Social learning: Collaborative learning with large language models

DevFeed: [Social learning: Collaborative learning with large language models](<https://devfeed.tech/articles/social-learning-collaborative-learning-with-large-language-models-28564.md>)

Original publisher: [Read original article](<http://blog.research.google/2024/03/social-learning-collaborative-learning.html>)

Author: Google AI (noreply@blogger.com)

Published: 2024-03-07T18:15:00Z

Content type: article

Language: en

Sources: [Google Research](<https://devfeed.tech/sources/google-research.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [datasets](<https://devfeed.tech/tags/datasets.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [few-shot](<https://devfeed.tech/tags/few-shot.md>), [few-shot-learning](<https://devfeed.tech/tags/few-shot-learning.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [machine-intelligence](<https://devfeed.tech/tags/machine-intelligence.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [research](<https://devfeed.tech/tags/research.md>), [use-cases](<https://devfeed.tech/tags/use-cases.md>)

### AI overview

This Google Research article presents a privacy-aware social learning framework in which large language models teach one another using natural language rather than shared gradients. It describes evaluations involving spam detection, grade-school mathematics, and text-based question answering, including settings where labeled examples cannot be directly shared because of privacy concerns.

### Source excerpt

Posted by Amirkeivan Mohtashami, Research Intern, and Florian Hartmann, Software Engineer, Google Research Large language models (LLMs) have significantly improved the state of the art for solving tasks specified using natural language, often reaching performance close to that of people. As these models increasingly enable assistive agents, it could be beneficial for them to learn effectively from each other, much like people do in social settings, which would allow LLM-based agents to improve each other's performance. To discuss the learning processes of humans, Bandura and Walters described the concept of social learning in 1977, outlining different models of observational learning used by people. One common method of learning from others is through a verbal instruction (e.g., from a teacher) that describes how to engage in a particular behavior. Alternatively, learning can happen through a live model by mimicking a live example of the behavior. Given the success of LLMs mimicking human communication, in our paper "Social Learning: Towards Collaborative Learning with Large Language Models", we investigate whether LLMs are able to learn from each other using social learning. To this end, we outline a framework for social learning in which LLMs share knowledge with each other in a privacy-aware manner using natural language. We evaluate the effectiveness of our framework on various datasets, and propose quantitative methods that measure privacy in this setting. In contrast to previous approaches to collaborative learning, such as common federated learning approaches that often rely on gradients, in our framework, agents teach each other purely using natural language. Social learning for LLMs To extend social learning to language models, we consider the scenario where a student LLM should learn to solve a task from multiple teacher entities that already know that task. In our paper, we evaluate the student's performance on a variety of tasks, such as spam detection i