Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation

• URL: http://arxiv.org/abs/2412.14487v3
• Date: Sun, 23 Feb 2025 13:18:26 GMT
• Title: Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation
• Authors: Jihao Gu, Yingyao Wang, Meng Cao, Pi Bu, Jun Song, Yancheng He, Shilong Li, Bo Zheng,
• Abstract summary: We propose a novel Token Preference Optimization model with self-calibrated rewards (dubbed as TPO)<n>Specifically, we introduce a token-level emphvisual-anchored emphreward as the difference of the logistic distributions of generated tokens conditioned on the raw image and the corrupted one.<n>To highlight the informative visual-anchored tokens, a visual-aware training objective is proposed to enhance more accurate token-level optimization.
• Score: 29.667702981248205
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Direct Preference Optimization (DPO) has been demonstrated to be highly effective in mitigating hallucinations in Large Vision Language Models (LVLMs) by aligning their outputs more closely with human preferences. Despite the recent progress, existing methods suffer from two drawbacks: 1) Lack of scalable token-level rewards; and 2) Neglect of visual-anchored tokens. To this end, we propose a novel Token Preference Optimization model with self-calibrated rewards (dubbed as TPO), which adaptively attends to visual-correlated tokens without fine-grained annotations. Specifically, we introduce a token-level \emph{visual-anchored} \emph{reward} as the difference of the logistic distributions of generated tokens conditioned on the raw image and the corrupted one. In addition, to highlight the informative visual-anchored tokens, a visual-aware training objective is proposed to enhance more accurate token-level optimization. Extensive experimental results have manifested the state-of-the-art performance of the proposed TPO. For example, by building on top of LLAVA-1.5-7B, our TPO boosts the performance absolute improvement for hallucination benchmarks.

Related papers

• A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models [94.49953824684853]
  We introduce a dynamic pruning framework, GlimpsePrune, inspired by human cognition.<n>It takes a data-driven ''glimpse'' and prunes irrelevant visual tokens in a single forward pass before answer generation.<n>An enhanced GlimpsePrune+ achieves 110% of the baseline performance while maintaining a similarly high pruning rate.
  arXiv  Detail & Related papers  (2025-08-03T02:15:43Z)
• Rethinking Visual Token Reduction in LVLMs under Cross-modal Misalignment [38.04426918886084]
  Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics.<n>Previous efforts have explored visual token reduction either prior to or within the large language models (LLMs)<n>We introduce VisionDrop, a training-free, visual-only pruning framework that selects informative visual tokens based on intra-modal (visual-to-visual) attention.
  arXiv  Detail & Related papers  (2025-06-27T14:55:40Z)
• IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation [70.2753541780788]
  We introduce an Information Gain-based Decisiveness-aware Token handling (IGD) strategy that integrates token decisiveness into both tuning and decoding.<n>IGD consistently improves recommendation accuracy, achieving significant gains on widely used ranking metrics compared to strong baselines.
  arXiv  Detail & Related papers  (2025-06-16T08:28:19Z)
• End-to-End Vision Tokenizer Tuning [73.3065542220568]
  The vision tokenizer optimized for low-level reconstruction is to downstream tasks requiring varied representations and semantics.<n>The loss of the vision tokenization can be the representation bottleneck for target tasks.<n>We propose ETT, an end-to-end vision tokenizer tuning approach that enables joint optimization between vision tokenization and target autoregressive tasks.
  arXiv  Detail & Related papers  (2025-05-15T17:59:39Z)
• TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model [56.43860351559185]
  We introduce textbfTopV, a compatible textbfTOken textbfPruning with inference Time Optimization for fast and low-memory textbfVLM. Our framework incorporates a visual-aware cost function to measure the importance of each source visual token, enabling effective pruning of low-importance tokens.
  arXiv  Detail & Related papers  (2025-03-24T01:47:26Z)
• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space. Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation [46.72611855060883]
  We propose an RLHF-equivalent distillation method for token-level reward optimization. Experimental results demonstrate the superiority of our AlignDistil over existing methods.
  arXiv  Detail & Related papers  (2025-03-04T17:57:09Z)
• Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability [55.29624228206882]
  Large Language Models (LLMs) have exhibited remarkable performance on reasoning tasks.<n>LLMs tend to produce positive outcomes when forced to decode other tokens instead of critical tokens.<n>We propose a novel approach - cDPO - designed to automatically recognize and conduct token-level rewards for the critical tokens.
  arXiv  Detail & Related papers  (2024-11-29T18:58:22Z)
• Systematic Reward Gap Optimization for Mitigating VLM Hallucinations [34.71750379630014]
  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.
  arXiv  Detail & Related papers  (2024-11-26T09:42:07Z)
• Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters [54.01228554126122]
  Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks. To reduce inference costs, one can either downsize the Large Language Models (LLMs) or reduce the number of input tokens needed to represent the image. We take the first steps toward designing token compression algorithms tailored for high-compression settings.
  arXiv  Detail & Related papers  (2024-11-05T18:54:21Z)
• Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment [57.0121616203175]
  We propose FiSAO, a novel self-alignment method that utilizes the model's own visual encoder as a fine-grained verifier to improve vision-language alignment. By leveraging token-level feedback from the vision encoder, FiSAO significantly improves vision-language alignment, even surpassing traditional preference tuning methods that require additional data.
  arXiv  Detail & Related papers  (2024-10-18T03:34:32Z)
• Calibrated Self-Rewarding Vision Language Models [27.686545023186852]
  Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. LVLMs often exhibit the hallucination phenomenon, where generated text responses appear linguistically plausible but contradict the input image. We propose the Calibrated Self-Rewarding (CSR) approach, which enables the model to self-improve by iteratively generating candidate responses, evaluating the reward for each response, and curating preference data for fine-tuning.
  arXiv  Detail & Related papers  (2024-05-23T14:30:33Z)
• Aligning Modalities in Vision Large Language Models via Preference Fine-tuning [67.62925151837675]
  In this work, we frame the hallucination problem as an alignment issue, tackle it with preference tuning. Specifically, we propose POVID to generate feedback data with AI models. We use ground-truth instructions as the preferred response and a two-stage approach to generate dispreferred data. In experiments across broad benchmarks, we show that we can not only reduce hallucinations, but improve model performance across standard benchmarks, outperforming prior approaches.
  arXiv  Detail & Related papers  (2024-02-18T00:56:16Z)
• Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention [36.90363317158731]
  We propose an adaptive sparse token pruning framework with a minimal cost. Our method improves the throughput of DeiT-S by 50% and brings only 0.2% drop in top-1 accuracy.
  arXiv  Detail & Related papers  (2022-09-28T03:07:32Z)
• Prompt-based Learning for Unpaired Image Captioning [86.44188293709307]
  Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Recent successes of Vision-Language Pre-Trained Models (VL-PTMs) have triggered the development of prompt-based learning. We present in this paper a novel scheme based on prompt to train the UIC model, making best use of the powerful generalization ability.
  arXiv  Detail & Related papers  (2022-05-26T03:13:43Z)

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.