One Minute NLP

Model Context Protocol

MCP is an open standard that defines how LLMs integrate with external tools, data, and context.

Aug 25 • 

Dasha Herrmannova

3

1

April 2025

In-context learning

In-context learning is a prompting technique that allows LLMs to learn and adapt to new tasks based on examples provided within the input prompt…

Apr 11 • 

Dasha Herrmannova

3

March 2025

Reflection agents

Reflection is a simple but powerful technique for improving the quality of LLM responses by prompting the LLM to reflect on its own output to identify…

Mar 30 • 

Dasha Herrmannova

2

Top-k and top-p sampling

Top-k and top-p sampling are methods used to control the randomness and diversity of LLM outputs.

Mar 20 • 

Dasha Herrmannova

5

Reasoning Models

Reasoning models are a new class of LLMs designed to solve complex problems like math and coding.

Mar 12 • 

Dasha Herrmannova

7

Group Relative Policy Optimization

Group Relative Policy Optimization (GRPO) is a reinforcement learning algorithm that was used to train DeepSeek-R1.

Mar 3 • 

Dasha Herrmannova

4

February 2025

Proximal Policy Optimization

Proximal Policy Optimization is frequently used in Reinforcement Learning from Human Feedback to further train LLMs after supervised fine-tuning. It was…

Feb 25 • 

Dasha Herrmannova

2

RLHF

Reinforcement Learning from Human Feedback is a training phase used on LLMs after supervised fine-tuning to further improve LLM responses. It was one of…

Feb 15 • 

Dasha Herrmannova

2

ReAct Agent Model

ReAct (Reason + Act) is a design pattern for AI agents that incorporates planning and action execution. It has become a common way to implement agents.

Feb 6 • 

Dasha Herrmannova

5

January 2025

Knowledge Distillation

Knowledge Distillation is a popular technique for transferring knowledge from large, powerful models to smaller, more efficient models.

Jan 29 • 

Dasha Herrmannova

5

Mixture of Experts

Mixture of Experts (MoE) is an ensemble learning technique that enables creating larger models without increasing training and inference cost.

Jan 19 • 

Dasha Herrmannova

July 2024

Low-Rank Adaptation

Low-Rank Adaptation (LoRA) is a popular method for Parameter-Efficient Fine-Tuning of Large Language Models. LoRA significantly improves fine-tuning…

Jul 25, 2024 • 

Dasha Herrmannova

1