# Caption Injection for Optimization in Generative Search Engine

arXiv: https://arxiv.org/abs/2511.04080 · HTML: https://mlsanity.com/paper/2511.04080/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 6 Nov 2025.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [Improving CLIP Training with Language Rewrites](https://mlsanity.com/paper/2305.20088/) (2023)
- [The Revolution of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2402.12451/) (2024)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [CapsFusion: Rethinking Image-Text Data at Scale](https://mlsanity.com/paper/2310.20550/) (2023)
- [Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities](https://mlsanity.com/paper/2505.02567/) (2025)
- [VeCLIP: Improving CLIP Training via Visual-enriched Captions](https://mlsanity.com/paper/2310.07699/) (2023)
- [GEO: Generative Engine Optimization](https://mlsanity.com/paper/2311.09735/) (2023)
- [Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image](https://mlsanity.com/paper/2006.05398/) (2020)
- [Adversarial Search Engine Optimization for Large Language Models](https://mlsanity.com/paper/2406.18382/) (2024)
- [FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions](https://mlsanity.com/paper/2305.17718/) (2023)
- [Manipulating Large Language Models to Increase Product Visibility](https://mlsanity.com/paper/2404.07981/) (2024)
- [Ranking Manipulation for Conversational Search Engines](https://mlsanity.com/paper/2406.03589/) (2024)
- [Context Understanding in Computer Vision: A Survey](https://mlsanity.com/paper/2302.05011/) (2023)
- [Vision+X: A Survey on Multimodal Learning in the Light of Data](https://mlsanity.com/paper/2210.02884/) (2022)
- [Enhancing Interactive Image Retrieval With Query Rewriting Using Large Language Models and Vision Language Models](https://mlsanity.com/paper/2404.18746/) (2024)
- [Altogether: Image Captioning via Re-aligning Alt-text](https://mlsanity.com/paper/2410.17251/) (2024)
- [MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation](https://mlsanity.com/paper/2502.04176/) (2025)
- [Leveraging Large Language Models for Multimodal Search](https://mlsanity.com/paper/2404.15790/) (2024)
- [Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines](https://mlsanity.com/paper/2411.16365/) (2024)
- [Zero-Shot Action Recognition from Diverse Object-Scene Compositions](https://mlsanity.com/paper/2110.13479/) (2021)
- [MuRAR: A Simple and Effective Multimodal Retrieval and Answer Refinement Framework for Multimodal Question Answering](https://mlsanity.com/paper/2408.08521/) (2024)
- [Role-Augmented Intent-Driven Generative Search Engine Optimization](https://mlsanity.com/paper/2508.11158/) (2025)

## Built on by (most cited first, 2 of 2)

- [IF-GEO: Conflict-Aware Instruction Fusion for Multi-Query Generative Engine Optimization](https://mlsanity.com/paper/2601.13938/) (2026)
- [Mechanism Design for Generative Engines: From Exploitation toward Win-Win Outcomes](https://mlsanity.com/paper/2608.11390/) (2026)

## Abstract (arXiv)

Generative Search Engine (GSE) leverages the Retrieval-Augmented Generation (RAG) technique and the Large Language Model (LLM) to integrate multi-source information and provide users with accurate and comprehensive responses. Unlike traditional search engines that present results in ranked lists, GSE shifts users' attention from sequential browsing to content-driven subjective perception, not only driving a paradigm shift in information retrieval but also highlighting the importance of enhancing the subjective visibility of content in generative search. In this context, Generative Search Engine Optimization (G-SEO) methods have emerged as a new research focus. With the rapid advancement of Multimodal Retrieval-Augmented Generation (MRAG) techniques, GSE can now efficiently integrate text, images, audio, and video, producing richer responses that better satisfy complex information needs. Existing G-SEO methods, however, remain limited to text-based optimization and fail to fully exploit multimodal data. To address this gap, we propose Caption Injection, the first multimodal G-SEO approach, which extracts captions from images and injects them into textual content, integrating visual semantics to enhance the subjective visibility in generative search. We systematically evaluate Caption Injection on MRAMG, a benchmark for MRAG, under both unimodal and multimodal settings. Experimental results show that Caption Injection significantly outperforms text-only G-SEO baselines under the G-EVAL metric, effectively improving the subjective visibility of content perceived by users, and demonstrating the practical benefits of multimodal information in G-SEO. The source code for this work is openly available at https://github.com/GrayChan04/Caption-Injection.