---
title: "UniMS-RAG: Unified Multi-Source RAG for Personalised Dialogue"
description: "UniMS-RAG: Unified Multi-Source RAG for Personalised Dialogue\n\nConsiderable development has taken place in the area of RAG, especially in adding structure and multi-document approaches.UniMS-RAG: Unified Multi-Source RAG for Personalised Dialogue\nConsiderable development has taken place in the area of RAG, especially in adding structure and multi-document approaches."
---

[Cobus Greyling](https://blog.kore.ai/cobus-greyling)

# [UniMS-RAG: Unified Multi-Source RAG for Personalised Dialogue](https://blog.kore.ai/cobus-greyling/unims-rag-unified-multi-source-rag-for-personalised-dialogue-1)

 Written by [Cobus Greyling](https://blog.kore.ai/cobus-greyling/author/cobus-greyling) | Mar 31, 2025 9:42:41 AM

***This study explores how the RAG process can be decomposed, adding elements like multi-document retrieval, memory and personal information.***

# Overview

- Large Language Models (LLMs) excel in natural language tasks but face challenges in personalisation & context within dialogue systems.
- The study proposes a Unified Multi-Source Retrieval-Augmented Generation system (UniMS-RAG) to address personalisation issues by decomposing tasks into Knowledge Source Selection, Knowledge Retrieval, and Response Generation.

- The system includes a self-refinement mechanism that iteratively refines generated responses based on consistency scores between the response and retrieved evidence.  
  Experimental results demonstrate UniMS-RAG’s state-of-the-art performance in knowledge source selection and response generation tasks.

[Source](https://arxiv.org/pdf/2401.13256.pdf)

- The diagram above, shows two scenarios, where the user and bot persona are independent and (in the second example) inter-dependent.
- For the inter-dependent approach there needs to be evaluation tokens, and acting tokens.

# Considerations

## Knowledge Source Selection

Intelligent and accurate knowledge source selection, together with synthesising multiple information sources into one coherent and succinct answer will become crucial.

## Introduction of Complexity

One of the allures of RAG use to be the simplicity of implementation. However, considerable work is being done in terms of Agentic RAG, multi-document search and adding elements like conversational history and more.

Agentic RAG is where a hierarchy of agents are combined with a RAG implementation. The introduction of complexity and enhanced intelligence are inevitable.

## Personalisation & Context

Personalisation and maintaining context via conversational history are both important elements for stellar UX. UniMS-RAG prioritises these elements with their proposed RAG structure.

## Continuous improvement

The study includes an algorithm for Inference with Self-refinement, coupled with the fact that RAG in general lends a great degree of inspectability and observability.

# UniMS-RAG Framework

UniMS-RAG unifies the training process for ***planning***, ***retrieving***, and ***reading***tasks, integrating them into a comprehensive framework.

Leveraging the power of large language models (LLMs) to harness external knowledge sources, UniMS-RAG enhances LLMs’ ability to seamlessly connect diverse sources in personalised knowledge-grounded dialogues.

This integration simplifies the traditionally separate retriever and reader training tasks, allowing adaptive evidence retrieval and relevance score evaluation in a unified manner.

The image below is an illustration of the proposed method called **UniMS-RAG.** Three optimisation tasks are carefully designed:

1. Knowledge Source Selection
2. Relevance Score Prediction
3. Response Generation.

## **Planning**

This is the process of creating a series of decisions on which specific knowledge source should be used, given the relationship between different sources.

## Retrieval

Retrieve the top-n results from external databases according to the decisions.

## Generation

Incorporate all retrieved knowledge into the final response generation.

[Source](https://arxiv.org/pdf/2401.13256.pdf)

# Final Thoughts

This approach seeks to address personalised knowledge-grounded dialogue tasks in a multi-source setting, breaking the problem into three sub-tasks: knowledge source selection, knowledge retrieval, and response generation.

The proposed Unified Multi-Source Retrieval-Augmented Dialogue System (UniMS-RAG) uses Large Language Models (LLMs) as planners, retrievers, and readers simultaneously.

The framework introduces self-refinement during inference, refining responses using consistency and similarity scores.

Experimental results on two datasets show UniMS-RAG generates more personalised and factual responses, outperforming baseline models.

 

Find the original study [here](https://arxiv.org/abs/2401.13256). 

[View full post](https://blog.kore.ai/cobus-greyling/unims-rag-unified-multi-source-rag-for-personalised-dialogue-1)

```json
{
  "@context" : "http://schema.org",
  "@type" : "BlogPosting",
  "author" : {
    "@type" : "Person",
    "name" : "Cobus Greyling"
  },
  "dateModified" : "2025-03-31T09:42:41.837Z",
  "datePublished" : "2025-03-31T09:42:41Z",
  "headline" : "UniMS-RAG: Unified Multi-Source RAG for Personalised Dialogue",
  "image" : {
    "@type" : "ImageObject",
    "height" : 914,
    "url" : "https://info.kore.ai/hubfs/2025-03-31_10-13-09%20SDG%20Cobus%20Greyling-1.jpg",
    "width" : 1762
  },
  "mainEntityOfPage" : "https://blog.kore.ai/cobus-greyling/unims-rag-unified-multi-source-rag-for-personalised-dialogue-1",
  "publisher" : {
    "@type" : "Organization",
    "logo" : {
      "@type" : "ImageObject",
      "height" : 60,
      "url" : "/hs/hsstatic/content_shared_assets/static-1.4092/img/default-amp-logo.png",
      "width" : 60
    },
    "name" : "Cobus Greyling"
  }
}
```