Saved in:
Bibliographic Details
Main Authors: Li, Tianyuan, Wang, Lei, Ahmat, Ahtamjan, Yang, Yating, Ma, Bo, Dong, Rui, Han, Bangju
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.17359
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909881516163072
author Li, Tianyuan
Wang, Lei
Ahmat, Ahtamjan
Yang, Yating
Ma, Bo
Dong, Rui
Han, Bangju
author_facet Li, Tianyuan
Wang, Lei
Ahmat, Ahtamjan
Yang, Yating
Ma, Bo
Dong, Rui
Han, Bangju
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17359
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MLLM-Driven Semantic Identifier Generation for Generative Cross-Modal Retrieval
Li, Tianyuan
Wang, Lei
Ahmat, Ahtamjan
Yang, Yating
Ma, Bo
Dong, Rui
Han, Bangju
Information Retrieval
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.
title MLLM-Driven Semantic Identifier Generation for Generative Cross-Modal Retrieval
topic Information Retrieval
url https://arxiv.org/abs/2509.17359