Multimodal LLMs (MLLMs) are the natural extension of large language models to handle multimodal inputs, combining text and image data. They have recently garnered attention due to their capability to address complex tasks involving both modalities. However, their effectiveness is limited to the knowledge acquired during training, which restricts their practical utility. In this work, we introduce a novel method to enhance the adaptability of MLLMs by integrating external knowledge sources. Our proposed model, Reflective LLaVA (ReflectiVA), utilizes reflective tokens to dynamically determine the need for external knowledge and predict the relevance of information retrieved from an external database. Tokens are trained following a two-stage two-model training recipe. This ultimately enables the MLLM to manage external knowledge while preserving fluency and performance on tasks where external knowledge is not needed. Through our experiments, we demonstrate the efficacy of ReflectiVA for knowledge-based visual question answering, highlighting its superior performance compared to existing methods. Source code and trained models are publicly available at https://github.com/aimagelab/ReflectiVA.

Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering / Cocchi, Federico; Moratelli, Nicholas; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita. - (2025). (Intervento presentato al convegno IEEE/CVF Conference on Computer Vision and Pattern Recognition tenutosi a Nashville TN nel June 11th - June 15th).

Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering

Federico Cocchi;Nicholas Moratelli;Marcella Cornia;Lorenzo Baraldi;Rita Cucchiara
2025

Abstract

Multimodal LLMs (MLLMs) are the natural extension of large language models to handle multimodal inputs, combining text and image data. They have recently garnered attention due to their capability to address complex tasks involving both modalities. However, their effectiveness is limited to the knowledge acquired during training, which restricts their practical utility. In this work, we introduce a novel method to enhance the adaptability of MLLMs by integrating external knowledge sources. Our proposed model, Reflective LLaVA (ReflectiVA), utilizes reflective tokens to dynamically determine the need for external knowledge and predict the relevance of information retrieved from an external database. Tokens are trained following a two-stage two-model training recipe. This ultimately enables the MLLM to manage external knowledge while preserving fluency and performance on tasks where external knowledge is not needed. Through our experiments, we demonstrate the efficacy of ReflectiVA for knowledge-based visual question answering, highlighting its superior performance compared to existing methods. Source code and trained models are publicly available at https://github.com/aimagelab/ReflectiVA.
2025
IEEE/CVF Conference on Computer Vision and Pattern Recognition
Nashville TN
June 11th - June 15th
Cocchi, Federico; Moratelli, Nicholas; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering / Cocchi, Federico; Moratelli, Nicholas; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita. - (2025). (Intervento presentato al convegno IEEE/CVF Conference on Computer Vision and Pattern Recognition tenutosi a Nashville TN nel June 11th - June 15th).
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1373629
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact