Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912557505183744 |
|---|---|
| author | Compagnoni, Alberto Caffagni, Davide Moratelli, Nicholas Baraldi, Lorenzo Cornia, Marcella Cucchiara, Rita |
| author_facet | Compagnoni, Alberto Caffagni, Davide Moratelli, Nicholas Baraldi, Lorenzo Cornia, Marcella Cucchiara, Rita |
| contents | Multimodal Large Language Models (MLLMs) emerge as a unified interface to address a multitude of tasks, ranging from NLP to computer vision. Despite showcasing state-of-the-art results in many benchmarks, a long-standing issue is the tendency of MLLMs to hallucinate, that is to generate answers to the user's query that are not reflected in the visual input. In this paper, we address the problem of hallucinations as an alignment problem, seeking to steer the MLLM so that it prefers generating content without hallucinations. In contrast to recent approaches that require complicated pipelines to build synthetic preference data for alignment training, often relying on proprietary models, we capitalize on the well-known CHAIR metric, originally proposed to gauge the degree of hallucinations in image captioning. Given a pair of generated answers, we leverage CHAIR to distinguish winner and loser options (i.e., non-hallucinated and hallucinated samples) and fine-tune off-the-shelf MLLMs via Direct Preference Optimization (DPO). The resulting method, which we refer to as CHAIR-DPO, effectively diminishes the amount of hallucinated answers on several hallucination benchmarks, demonstrating the effectiveness of fine-tuning the MLLM with a CHAIR-based reward. Source code and trained models are publicly available at https://github.com/aimagelab/CHAIR-DPO. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_20181 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization Compagnoni, Alberto Caffagni, Davide Moratelli, Nicholas Baraldi, Lorenzo Cornia, Marcella Cucchiara, Rita Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Multimedia Multimodal Large Language Models (MLLMs) emerge as a unified interface to address a multitude of tasks, ranging from NLP to computer vision. Despite showcasing state-of-the-art results in many benchmarks, a long-standing issue is the tendency of MLLMs to hallucinate, that is to generate answers to the user's query that are not reflected in the visual input. In this paper, we address the problem of hallucinations as an alignment problem, seeking to steer the MLLM so that it prefers generating content without hallucinations. In contrast to recent approaches that require complicated pipelines to build synthetic preference data for alignment training, often relying on proprietary models, we capitalize on the well-known CHAIR metric, originally proposed to gauge the degree of hallucinations in image captioning. Given a pair of generated answers, we leverage CHAIR to distinguish winner and loser options (i.e., non-hallucinated and hallucinated samples) and fine-tune off-the-shelf MLLMs via Direct Preference Optimization (DPO). The resulting method, which we refer to as CHAIR-DPO, effectively diminishes the amount of hallucinated answers on several hallucination benchmarks, demonstrating the effectiveness of fine-tuning the MLLM with a CHAIR-based reward. Source code and trained models are publicly available at https://github.com/aimagelab/CHAIR-DPO. |
| title | Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Multimedia |
| url | https://arxiv.org/abs/2508.20181 |