Re-ranking the Context for Multimodal Retrieval Augmented Generation
- URL: http://arxiv.org/abs/2501.04695v1
- Date: Wed, 08 Jan 2025 18:58:22 GMT
- Title: Re-ranking the Context for Multimodal Retrieval Augmented Generation
- Authors: Matin Mortaheb, Mohammad A. Amir Khojastepour, Srimat T. Chakradhar, Sennur Ulukus,
- Abstract summary: Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context.
RAG systems face unique challenges: (i) the retrieval process may select irrelevant entries to user query (e.g., images, documents), and (ii) vision-language models or multi-modal language models like GPT-4o may hallucinate when processing these entries to generate RAG output.
We show that by using a more advanced relevancy measure, one can enhance the retrieval process by selecting more relevant pieces from the knowledge-base and eliminate
- Score: 28.63893944806149
- License:
- Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge to generate a response within a context with improved accuracy and reduced hallucinations. However, multi-modal RAG systems face unique challenges: (i) the retrieval process may select irrelevant entries to user query (e.g., images, documents), and (ii) vision-language models or multi-modal language models like GPT-4o may hallucinate when processing these entries to generate RAG output. In this paper, we aim to address the first challenge, i.e, improving the selection of relevant context from the knowledge-base in retrieval phase of the multi-modal RAG. Specifically, we leverage the relevancy score (RS) measure designed in our previous work for evaluating the RAG performance to select more relevant entries in retrieval process. The retrieval based on embeddings, say CLIP-based embedding, and cosine similarity usually perform poorly particularly for multi-modal data. We show that by using a more advanced relevancy measure, one can enhance the retrieval process by selecting more relevant pieces from the knowledge-base and eliminate the irrelevant pieces from the context by adaptively selecting up-to-$k$ entries instead of fixed number of entries. Our evaluation using COCO dataset demonstrates significant enhancement in selecting relevant context and accuracy of the generated response.
Related papers
- RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance [28.63893944806149]
Retrieval-augmented generation (RAG) improves large language models by using external knowledge to guide response generation, reducing hallucinations.
RAG can introduce new hallucination sources: (i) the retrieval process may select irrelevant pieces as raw context from the database, and (ii) retrieved images are processed into text-based context.
We propose a novel framework to evaluate the reliability of multi-modal RAG using two performance measures: (i) the relevancy score (RS), assessing the relevance of retrieved entries to the query, and (ii) the correctness score (CS), evaluating the accuracy of the generated response
arXiv Detail & Related papers (2025-01-07T18:52:05Z) - VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation [100.06122876025063]
This paper introduces VisDoMBench, the first comprehensive benchmark designed to evaluate QA systems in multi-document settings.
We propose VisDoMRAG, a novel multimodal Retrieval Augmented Generation (RAG) approach that simultaneously utilizes visual and textual RAG.
arXiv Detail & Related papers (2024-12-14T06:24:55Z) - Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation [72.70046559930555]
We propose a generic RAG approach called Adaptive Note-Enhanced RAG (Adaptive-Note) for complex QA tasks.
Specifically, Adaptive-Note introduces an overarching view of knowledge growth, iteratively gathering new information in the form of notes.
In addition, we employ an adaptive, note-based stop-exploration strategy to decide "what to retrieve and when to stop" to encourage sufficient knowledge exploration.
arXiv Detail & Related papers (2024-10-11T14:03:29Z) - SMART-RAG: Selection using Determinantal Matrices for Augmented Retrieval [40.17823569905232]
Retrieval-Augmented Generation (RAG) has greatly improved large language models (LLMs) by enabling them to generate accurate, contextually grounded responses.
RAG approaches, which prioritize top-ranked documents based solely on query-context relevance, often introduce redundancy and conflicting information.
We propose Selection using Matrices for Augmented Retrieval (RAG) in question answering tasks, a fully unsupervised and training-free framework designed to optimize context selection in RAG.
arXiv Detail & Related papers (2024-09-21T03:03:09Z) - Better RAG using Relevant Information Gain [1.5604249682593647]
A common way to extend the memory of large language models (LLMs) is by retrieval augmented generation (RAG)
We propose a novel simple optimization metric based on relevant information gain, a probabilistic measure of the total information relevant to a query for a set of retrieved results.
When used as a drop-in replacement for the retrieval component of a RAG system, this method yields state-of-the-art performance on question answering tasks.
arXiv Detail & Related papers (2024-07-16T18:09:21Z) - Optimization of Retrieval-Augmented Generation Context with Outlier Detection [0.0]
We focus on methods to reduce the size and improve the quality of the prompt context required for question-answering systems.
Our goal is to select the most semantically relevant documents, treating the discarded ones as outliers.
It was found that the greatest improvements were achieved with increasing complexity of the questions and answers.
arXiv Detail & Related papers (2024-07-01T15:53:29Z) - ACE: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling [53.97609687516371]
We propose a pioneering generAtive Cross-modal rEtrieval framework (ACE) for end-to-end cross-modal retrieval.
ACE achieves state-of-the-art performance in cross-modal retrieval and outperforms the strong baselines on Recall@1 by 15.27% on average.
arXiv Detail & Related papers (2024-06-25T12:47:04Z) - RAGGED: Towards Informed Design of Retrieval Augmented Generation Systems [51.171355532527365]
Retrieval-augmented generation (RAG) can significantly improve the performance of language models (LMs)
RAGGED is a framework for analyzing RAG configurations across various document-based question answering tasks.
arXiv Detail & Related papers (2024-03-14T02:26:31Z) - CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models [49.16989035566899]
Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources.
This paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios.
arXiv Detail & Related papers (2024-01-30T14:25:32Z) - Corrective Retrieval Augmented Generation [36.04062963574603]
Retrieval-augmented generation (RAG) relies heavily on relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong.
We propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation.
CRAG is plug-and-play and can be seamlessly coupled with various RAG-based approaches.
arXiv Detail & Related papers (2024-01-29T04:36:39Z) - End-to-end Knowledge Retrieval with Multi-modal Queries [50.01264794081951]
ReMuQ requires a system to retrieve knowledge from a large corpus by integrating contents from both text and image queries.
We introduce a retriever model ReViz'' that can directly process input text and images to retrieve relevant knowledge in an end-to-end fashion.
We demonstrate superior performance in retrieval on two datasets under zero-shot settings.
arXiv Detail & Related papers (2023-06-01T08:04:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.