Freeret: Mllms As Training-free Retrievers

Abstract

Multimodal large language models (MLLMs) are emerging as versatile foundations for mixed-modality retrieval. Yet, they often require heavy post-hoc training to convert them into contrastive encoders for retrieval. This work asks: Can off-the-shelf MLLMs serve as powerful retrievers without additional training? We present FreeRet, a plug-and-play framework that turns any MLLM into a two-stage retriever. FreeRet first derives semantically grounded embeddings directly from the model for fast candidate search, and then exploits its reasoning ability for precise reranking. The framework contributes three advances: bypassing lexical alignment layers to obtain semantically faithful embeddings, conditioning representation generation with explicit priors, and mitigating framing effect in reranking via neutral choice framing. On the MMEB and MMEB-V2 benchmarks spanning 46 datasets, FreeRet substantially outperforms models trained on millions of pairs. Beyond benchmarks, FreeRet is model-agnostic

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhu2025freeret

Related papers

• RETLLM: Training And Data-free Mllms For Multimodal Information Retrieval (2026)1.57
• Mm-embed: Universal Multimodal Retrieval With Multimodal Llms (2024)0.00
• Indexing Multimodal Language Models For Large-scale Image Retrieval (2026)0.00
• Lamra: Large Multimodal Model As Your Advanced Retrieval Assistant (2024)7.50
• SLQ: Bridging Modalities Via Shared Latent Queries For Retrieval With Frozen Mllms (2026)0.00
• CREM: Compression-driven Representation Enhancement For Multimodal Retrieval And Comprehension (2026)0.00
• Lightretriever: A Llm-based Text Retrieval Architecture With Extremely Faster Query Inference (2025)0.00
• Generative Giants, Retrieval Weaklings: Why Do Multimodal Large Language Models Fail At Multimodal Retrieval? (2025)0.00