# MLLM-Driven Semantic Identifier Generation for Generative Cross-Modal Retrieval

arXiv: https://arxiv.org/abs/2509.17359 · HTML: https://mlsanity.com/paper/2509.17359/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- First posted on arXiv 22 Sep 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Abstract (arXiv)

Generative cross-modal retrieval, which treats retrieval as a generation task, has emerged as a promising direction with the rise of Multimodal Large Language Models (MLLMs). In this setting, the model responds to a text query by generating an identifier corresponding to the target image. However, existing methods typically rely on manually crafted string IDs, clustering-based labels, or atomic identifiers requiring vocabulary expansion, all of which face challenges in semantic alignment or scalability.To address these limitations, we propose a vocabulary-efficient identifier generation framework that prompts MLLMs to generate Structured Semantic Identifiers from image-caption pairs. These identifiers are composed of concept-level tokens such as objects and actions, naturally aligning with the model's generation space without modifying the tokenizer. Additionally, we introduce a Rationale-Guided Supervision Strategy, prompting the model to produce a one-sentence explanation alongside each identifier serves as an auxiliary supervision signal that improves semantic grounding and reduces hallucinations during training.