<img src="https://secure.item0self.com/192096.png" alt="" style="display:none;">

Kore.ai Technical Blog

One-stop for everything related to AI-first
experience automation

Chain-of-Instructions (CoI) Fine-Tuning

This approach draws inspiration from Chain-of-Thought (CoT) prompting which generates step-by-step rationales from...

Read More

Performing Multiple LLM Calls & Voting On The Best Result Are Subject To Scaling Laws

More LLM calls enhance performance on easy queries but diminish it on hard ones.
So what scaling laws can be...

Read More

Exploring the Purpose, Power & Potential of Small Language Models (SLMs)

A number of very capable Small Language Models (SLMs) have been open-sourced recently. In this article you will find...

Read More

Self-Reflective Retrieval-Augmented Generation (SELF-RAG)

The SELF-RAG framework trains a single arbitrary language model to adaptively retrieve passages on-demand.To generate...

Read More

Prompt-RAG

Vector Embedding Free Retrieval-Augmented Generation

While Prompt-RAG does come with its limitations, it can...

Read More

Please Stop Saying Long Context Windows Will Replace RAG

And I’m curious to know if anyone has innovative approaches to using long context windows efficiently?

Long Context...

Read More

LLMs Training SLMs

Research from Microsoft Research shows how they used LLMs to train SLMs without any RLHF…

The primary focus in training...

Read More

The Evolution of Grounding & Planning In AI Agents

Simply put, intents are categories or classes used to classify conversations.Each interaction between a user and the...

Read More

The Shift From Large Language Models to Smaller, Vision-Enhanced Models & The Rise of AI Agents— Version 6

In recent developments within AI research, the focus has gradually shifted from reliance on Large Language Models...

Read More

LLM Drift, Prompt Drift & Cascading

Prompt Chaining can be performed manually or automatically; manual entails crafting chains by hand, via a GUI chain...

Read More

Leave Comment

Close menu