# Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

arXiv: https://arxiv.org/abs/2405.18654 · HTML: https://mlsanity.com/paper/2405.18654/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination mitigation in LVLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- First posted on arXiv 28 May 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Hallucination mitigation in LVLMs](https://mlsanity.com/mllm/hallucination-mitigation-in-lvlms/)

## Built on by (most cited first, 30 of 42)

- [mDPO: Conditional Preference Optimization for Multimodal Large Language Models](https://mlsanity.com/paper/2406.11839/) (2024)
- [AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving](https://mlsanity.com/paper/2412.15206/) (2024)
- [CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs](https://mlsanity.com/paper/2501.16629/) (2025)
- [Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization](https://mlsanity.com/paper/2502.13146/) (2025)
- [Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs](https://mlsanity.com/paper/2503.08342/) (2025)
- [MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2507.09184/) (2025)
- [SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes](https://mlsanity.com/paper/2601.05600/) (2026)
- [OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination](https://mlsanity.com/paper/2509.00723/) (2025)
- [Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention](https://mlsanity.com/paper/2511.20032/) (2025)
- [Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization](https://mlsanity.com/paper/2508.20181/) (2025)
- [Do Images Speak Louder than Words? Investigating the Effect of Textual Misinformation in VLMs](https://mlsanity.com/paper/2601.19202/) (2026)
- [Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation](https://mlsanity.com/paper/2510.22067/) (2025)
- [Exposing Hallucinations To Suppress Them: VLMs Representation Editing With Generative Anchors](https://mlsanity.com/paper/2509.21997/) (2025)
- [Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigation](https://mlsanity.com/paper/2512.00706/) (2025)
- [Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination](https://mlsanity.com/paper/2608.07302/) (2026)
- [Reflective Preference Optimization (RPO): Enhancing On-Policy Alignment via Hint-Guided Reflection](https://mlsanity.com/paper/2512.13240/) (2025)
- [One Token, Two Fates: A Unified Framework via Vision Token Manipulation Against MLLMs Hallucination](https://mlsanity.com/paper/2603.10360/) (2026)
- [ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs](https://mlsanity.com/paper/2606.31054/) (2026)
- [Towards Hallucination-Free Music: A Reinforcement Learning Preference Optimization Framework for Reliable Song Generation](https://mlsanity.com/paper/2508.05011/) (2025)
- [Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs](https://mlsanity.com/paper/2509.24491/) (2025)
- [VaPR -- Vision-language Preference alignment for Reasoning](https://mlsanity.com/paper/2510.01700/) (2025)
- [MM-THEBench: Do Reasoning MLLMs Think Reasonably?](https://mlsanity.com/paper/2601.22735/) (2026)
- [SAKED: Mitigating Hallucination in Large Vision-Language Models via Stability-Aware Knowledge Enhanced Decoding](https://mlsanity.com/paper/2602.09825/) (2026)
- [Aligning with Your Own Voice: Self-Corrected Preference Learning for Hallucination Mitigation in LVLMs](https://mlsanity.com/paper/2604.24395/) (2026)
- [The Truth Stays in the Family: Enhancing Contextual Grounding via Inherited Truthful Heads in Model Lineages](https://mlsanity.com/paper/2606.15821/) (2026)
- [Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation](https://mlsanity.com/paper/2606.29805/) (2026)
- [CL3DOR: Contrastive Learning for 3D Large Multimodal Models via Odds Ratio on High-Resolution Point Clouds](https://mlsanity.com/paper/2501.03879/) (2025)
- [TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs](https://mlsanity.com/paper/2507.21584/) (2025)
- [Watermarking for Factuality: Guiding Vision-Language Models Toward Truth via Tri-layer Contrastive Decoding](https://mlsanity.com/paper/2510.14304/) (2025)
- [IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination](https://mlsanity.com/paper/2602.01769/) (2026)

## Abstract (arXiv)

Despite their significant advancements, Multimodal Large Language Models (MLLMs) often generate factually inaccurate information, referred to as hallucination. In this work, we address object hallucinations in MLLMs, where information is generated about an object not present in the input image. 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, while preserving their general vision-language capabilities. To fine-tune MLLMs with DPA, we first generate a set of `hallucinated' and `correct' response pairs through generative data augmentation by selectively altering the ground-truth information of the correct responses at a phrase level. The DPA loss is then used to train MLLMs to reduce the likelihood of hallucinated phrases compared to the correct ones. Our thorough evaluation on various benchmarks confirms the effectiveness of DPA in mitigating hallucination while retaining the out-of-the-box performance of the MLLMs on general tasks. For instance, MLLMs finetuned with DPA, which we refer to as Hallucination Attenuated Language and Vision Assistant (HALVA), improve F1 by up to 13.4% on hallucination visual question-answering and reduce the hallucination rate by up to 4.2% on image description tasks.