Systematic Reward Gap Optimization for Mitigating VLM Hallucinations

• URL: http://arxiv.org/abs/2411.17265v3
• Date: Mon, 23 Jun 2025 07:12:17 GMT
• Title: Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
• Authors: Lehan He, Zeren Chen, Zhelun Shi, Tianyu Yu, Jing Shao, Lu Sheng,
• Abstract summary: We introduce Topic-level Preference Rewriting (TPR), a novel framework designed for the systematic optimization of reward gap configuration.<n>TPR provides topic-level control over fine-grained semantic details, enabling advanced data curation strategies.<n>It significantly reduces hallucinations by up to 93% on ObjectHal-Bench, and also exhibits superior data efficiency towards robust and cost-effective VLM alignment.
• Score: 34.71750379630014
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The success of Direct Preference Optimization (DPO) in mitigating hallucinations in Vision Language Models (VLMs) critically hinges on the true reward gaps within preference pairs. However, current methods, typically relying on ranking or rewriting strategies, often struggle to optimize these reward gaps in a systematic way during data curation. A core difficulty lies in precisely characterizing and strategically manipulating the overall reward gap configuration, that is, the deliberate design of how to shape these reward gaps within each preference pair across the data. To address this, we introduce Topic-level Preference Rewriting(TPR), a novel framework designed for the systematic optimization of reward gap configuration. Through selectively replacing semantic topics within VLM responses with model's own resampled candidates for targeted rewriting, TPR can provide topic-level control over fine-grained semantic details. This precise control enables advanced data curation strategies, such as progressively adjusting the difficulty of rejected responses, thereby sculpting an effective reward gap configuration that guides the model to overcome challenging hallucinations. Comprehensive experiments demonstrate TPR achieves state-of-the-art performance on multiple hallucination benchmarks, outperforming previous methods by an average of 20%. Notably, it significantly reduces hallucinations by up to 93% on ObjectHal-Bench, and also exhibits superior data efficiency towards robust and cost-effective VLM alignment.

Related papers

• ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning [14.034412856423529]
  Direct Preference Optimization (DPO) has gained attention for its simplicity and computational efficiency in aligning large language models (LLMs)<n>Recent advancements have extended DPO to multimodal scenarios, achieving strong performance.<n>Traditional DPO relies on binary preference optimization, rewarding or penalizing entire responses without considering fine-grained segment correctness.<n>We propose Adaptive Sentence-level Preference Optimization (ASPO), which evaluates individual sentences for more precise preference optimization.
  arXiv  Detail & Related papers  (2025-05-25T11:33:08Z)
• More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment [80.04449725137177]
  Direct Preference Optimization (DPO) has emerged as a simple, yet effective alternative to reinforcement learning from human feedback. Our study reveals a striking, safety-specific phenomenon associated with DPO alignment. Using solely self-generated responses for both chosen and rejected pairs significantly outperforms configurations that incorporate responses from stronger models.
  arXiv  Detail & Related papers  (2025-04-03T00:36:40Z)
• SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner [35.843587407696006]
  Large Visual Language Models (LVLMs) increasingly rely on preference alignment to ensure reliability.<n>We present projectname, a self-supervised framework capable of transforming the already abundant supervised text-image pairs into holistic preference triplets.
  arXiv  Detail & Related papers  (2025-03-06T08:33:11Z)
• Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization [18.855378039713678]
  Large Vision Language Models (VLMs) are prone to significant hallucinations, particularly in the form of cross-modal inconsistencies.<n>We introduce Re-Align, a novel alignment framework that leverages image retrieval to construct a dual-preference dataset.<n>We also introduce rDPO, an extension of the standard direct preference optimization that incorporates an additional visual preference objective during fine-tuning.
  arXiv  Detail & Related papers  (2025-02-18T18:59:57Z)
• Multimodal Preference Data Synthetic Alignment with Reward Model [23.978820500281213]
  We propose a new framework in generating synthetic data using a reward model as a proxy of human preference for effective multimodal alignment with DPO training. Experiment results indicate that integrating selected synthetic data, such as from generative and rewards models can effectively reduce reliance on human-annotated data.
  arXiv  Detail & Related papers  (2024-12-23T09:29:40Z)
• Uncertainty-Penalized Direct Preference Optimization [52.387088396044206]
  We develop a pessimistic framework for DPO by introducing preference uncertainty penalization schemes. The penalization serves as a correction to the loss which attenuates the loss gradient for uncertain samples. We show improved overall performance compared to vanilla DPO, as well as better completions on prompts from high-uncertainty chosen/rejected responses.
  arXiv  Detail & Related papers  (2024-10-26T14:24:37Z)
• VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment [55.7956150385255]
  We investigate the efficacy of AI feedback to scale supervision for aligning vision-language models. We introduce VLFeedback, the first large-scale vision-language feedback dataset. We train Silkie, an LVLM fine-tuned via direct preference optimization on VLFeedback.
  arXiv  Detail & Related papers  (2024-10-12T07:56:47Z)
• Reward-Augmented Data Enhances Direct Preference Alignment of LLMs [63.32585910975191]
  We introduce reward-conditioned Large Language Models (LLMs) that learn from the entire spectrum of response quality within the dataset.<n>We show that our approach consistently boosts DPO by a considerable margin.<n>Our method not only maximizes the utility of preference data but also mitigates the issue of unlearning, demonstrating its broad effectiveness beyond mere data expansion.
  arXiv  Detail & Related papers  (2024-10-10T16:01:51Z)
• In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement [71.60563181678323]
  Large language models (LLMs) have achieved great success across diverse tasks, and fine-tuning is sometimes needed to further enhance generation quality.<n>To handle these challenges, a direct solution is to generate high-confidence'' data from unsupervised downstream tasks.<n>We propose a novel approach, pseudo-supervised demonstrations aligned prompt optimization (PAPO) algorithm, which jointly refines both the prompt and the overall pseudo-supervision.
  arXiv  Detail & Related papers  (2024-10-04T03:39:28Z)
• Model-based Preference Optimization in Abstractive Summarization without Human Feedback [5.438770095369458]
  We introduce Model-based Preference Optimization (MPO) to fine-tune Large Language Models for improved summarization abilities without any human feedback. Our experiments on standard summarization datasets and various metrics demonstrate that our proposed MPO significantly enhances the quality of generated summaries without relying on human feedback.
  arXiv  Detail & Related papers  (2024-09-27T10:35:45Z)
• Self-supervised Preference Optimization: Enhance Your Language Model with Preference Degree Awareness [27.43137305486112]
  We propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-09-26T12:37:26Z)
• The Hitchhiker's Guide to Human Alignment with *PO [43.4130314879284]
  We focus on identifying the algorithm that, while being performant, is simultaneously more robust to varying hyper parameters. Our analysis reveals that the widely adopted DPO method consistently produces lengthy responses of inferior quality. Motivated by these findings, we propose an embarrassingly simple extension to the DPO algorithm, LN-DPO, resulting in more concise responses without sacrificing quality.
  arXiv  Detail & Related papers  (2024-07-21T17:35:20Z)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
  Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
  arXiv  Detail & Related papers  (2024-06-04T20:33:22Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences.<n>To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model.<n>Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• Debiasing Multimodal Large Language Models [61.6896704217147]
  Large Vision-Language Models (LVLMs) have become indispensable tools in computer vision and natural language processing. Our investigation reveals a noteworthy bias in the generated content, where the output is primarily influenced by the underlying Large Language Models (LLMs) prior to the input image. To rectify these biases and redirect the model's focus toward vision information, we introduce two simple, training-free strategies.
  arXiv  Detail & Related papers  (2024-03-08T12:35:07Z)
• SALMON: Self-Alignment with Instructable Reward Models [80.83323636730341]
  This paper presents a novel approach, namely SALMON, to align base language models with minimal human supervision. We develop an AI assistant named Dromedary-2 with only 6 exemplars for in-context learning and 31 human-defined principles.
  arXiv  Detail & Related papers  (2023-10-09T17:56:53Z)
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model [119.65409513119963]
  We introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form. The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight. Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods.
  arXiv  Detail & Related papers  (2023-05-29T17:57:46Z)
• Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision [84.31474052176343]
  Recent AI-assistant agents, such as ChatGPT, rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback to align the output with human intentions. This dependence can significantly constrain the true potential of AI-assistant agents due to the high cost of obtaining human supervision. We propose a novel approach called SELF-ALIGN, which combines principle-driven reasoning and the generative power of LLMs for the self-alignment of AI agents with minimal human supervision.
  arXiv  Detail & Related papers  (2023-05-04T17:59:28Z)

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.