Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization

• URL: http://arxiv.org/abs/2508.20181v1
• Date: Wed, 27 Aug 2025 18:02:04 GMT
• Title: Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization
• Authors: Alberto Compagnoni, Davide Caffagni, Nicholas Moratelli, Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara,
• Abstract summary: Multimodal Large Language Models (MLLMs) emerge as a unified interface to address a multitude of tasks.<n>Despite showcasing state-of-the-art results in many benchmarks, a long-standing issue is the tendency of MLLMs to hallucinate.<n>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.
• Score: 55.543583937522804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Look Closer! An Adversarial Parametric Editing Framework for Hallucination Mitigation in VLMs [6.645440928271175]
  Visionivate-Language Models (VLMs) have garnered increasing attention in the AI community due to their promising practical applications.<n>Recent studies attribute these hallucinations to VLMs' over-reliance on linguistic priors and insufficient visual feature integration.<n>We propose an adversarial parametric editing framework for Hallucination mitigation inVLMs, which follows an textbfActtextbfLocate-textbfEdit textbfAdversarially paradigm.
  arXiv  Detail & Related papers  (2025-12-26T11:56:45Z)
• PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning [87.35309934860938]
  hallucinations in large language models (MLLMs) are strongly associated with insufficient attention allocated to visual tokens.<n>We propose textbfPruneHal, a training-free, simple yet effective method that leverages adaptive KV cache pruning to enhance the model's focus on critical visual information.
  arXiv  Detail & Related papers  (2025-10-22T02:41:07Z)
• Mitigating Object Hallucination via Robust Local Perception Search [11.570368427723961]
  Local Perception Search (LPS) is a decoding method during inference that is both simple and training-free, yet effectively suppresses hallucinations.<n>We show that LPS significantly reduces the incidence of hallucinations compared to the baseline, showing exceptional performance, particularly in noisy settings.
  arXiv  Detail & Related papers  (2025-06-07T09:27:26Z)
• MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM [58.2298313720146]
  Multimodal hallucinations are multi-sourced and arise from diverse causes.<n>Existing benchmarks fail to adequately distinguish between perception-induced hallucinations and reasoning-induced hallucinations.
  arXiv  Detail & Related papers  (2025-05-30T05:54:36Z)
• MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation [50.73561815838431]
  Multimodal Large Language Models (MLLMs) frequently exhibit hallucination phenomena.<n>We present an empirical analysis and find that, although MLLMs incorrectly generate the objects in the final output, they are actually able to recognize visual objects in the preceding layers.<n>Motivated by this, we propose a novel dynamic correction decoding method for MLLMs DeCo, which adaptively selects the appropriate preceding layers and proportionally integrates knowledge into the final layer to adjust the output logits.
  arXiv  Detail & Related papers  (2024-10-15T16:57:44Z)
• Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs [54.50483041708911]
  Hallu-PI is the first benchmark designed to evaluate hallucination in MLLMs within Perturbed Inputs. Hallu-PI consists of seven perturbed scenarios, containing 1,260 perturbed images from 11 object types. Our research reveals a severe bias in MLLMs' ability to handle different types of hallucinations.
  arXiv  Detail & Related papers  (2024-08-02T16:07:15Z)
• Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment [52.43197107069751]
  Multimodal Large Language Models (MLLMs) often generate factually inaccurate information, referred to as hallucination.<n>We introduce Data-augmented Phrase-level Alignment (DPA), a novel loss which can be applied to instruction-tuned off-the-shelf MLLMs to mitigate hallucinations.
  arXiv  Detail & Related papers  (2024-05-28T23:36:00Z)
• Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback [40.930238150365795]
  We propose detecting and mitigating hallucinations in Large Vision Language Models (LVLMs) via fine-grained AI feedback.<n>We generate a small-size hallucination annotation dataset by proprietary models.<n>Then, we propose a detect-then-rewrite pipeline to automatically construct preference dataset for training hallucination mitigating model.
  arXiv  Detail & Related papers  (2024-04-22T14:46:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.