Pith. sign in

REVIEW 6 cited by

Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.21943 v1 pith:OOJOZCXE submitted 2024-10-29 cs.CL cs.AI

classification cs.CLcs.AI
keywords multimodalexperimentsimagesretrievaltextapproachimageindustrial
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) have demonstrated impressive capabilities in answering questions, but they lack domain-specific knowledge and are prone to hallucinations. Retrieval Augmented Generation (RAG) is one approach to address these challenges, while multimodal models are emerging as promising AI assistants for processing both text and images. In this paper we describe a series of experiments aimed at determining how to best integrate multimodal models into RAG systems for the industrial domain. The purpose of the experiments is to determine whether including images alongside text from documents within the industrial domain increases RAG performance and to find the optimal configuration for such a multimodal RAG system. Our experiments include two approaches for image processing and retrieval, as well as two LLMs (GPT4-Vision and LLaVA) for answer synthesis. These image processing strategies involve the use of multimodal embeddings and the generation of textual summaries from images. We evaluate our experiments with an LLM-as-a-Judge approach. Our results reveal that multimodal RAG can outperform single-modality RAG settings, although image retrieval poses a greater challenge than text retrieval. Additionally, leveraging textual summaries from images presents a more promising approach compared to the use of multimodal embeddings, providing more opportunities for future advancements.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RAVID: Retrieval-Augmented Visual Detection: A Knowledge-Driven Approach for AI-Generated Image Identification

    cs.CV 2025-08 conditional novelty 6.0 of 10

    RAVID detects AI-generated images by retrieving similar images from a database and feeding them to a vision-language model, reporting 93.85% average accuracy on UniversalFakeDetect.

  2. mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation

    cs.AI 2025-05 conditional novelty 6.0 of 10

    A systematic empirical study finds that for multimodal RAG, EVA-CLIP retrieval, listwise LVLM reranking, and feeding only the top-ranked document works best, with a self-reflection agent adding further gains.

  3. VISA: Retrieval Augmented Generation with Visual Source Attribution

    cs.IR 2024-12 conditional novelty 6.0 of 10

    VISA makes RAG output point to the exact bounding box in a document screenshot that supports the answer, and fine-tuned VLMs improve box accuracy from 1.5% to 54.2% on the new Wiki-VISA benchmark.

  4. HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Document

    cs.IR 2026-07 conditional novelty 5.0 of 10

    A holistic-view multimodal GraphRAG that conflict-resolves concept indices and retrieves via compact concept anchors plus modality-grouped evidence, beating strong baselines on three complex-document QA sets.

  5. Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks

    cs.IR 2025-01 conditional novelty 5.0 of 10

    Gradient-based pixel poisoning of a single document screenshot can rank it in the top-10 for up to 41.9% of unseen queries on DSE and 26.4% on ColPali.

  6. Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines

    cs.CL 2024-11 conditional novelty 5.0 of 10

    The authors create a 1,000-query multi-modal RAG benchmark with GPT-4o-based metrics, show multi-stage generation beats single-stage, and report fine-tuned 7B-8B models beating GPT-4o only in the single-stage comparison.

Pith tools