Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation
December 19, 2024 Β· Declared Dead Β· π Conference on Empirical Methods in Natural Language Processing
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Jihao Gu, Yingyao Wang, Meng Cao, Pi Bu, Jun Song, Yancheng He, Shilong Li, Bo Zheng
arXiv ID
2412.14487
Category
cs.CV: Computer Vision
Citations
3
Venue
Conference on Empirical Methods in Natural Language Processing
Last Checked
5 months ago
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.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Computer Vision
π
π
Old Age
π
π
Old Age
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
π
π
Old Age
SSD: Single Shot MultiBox Detector
π
π
Old Age
Squeeze-and-Excitation Networks
π
π
Old Age
Fast R-CNN
π
π
Old Age
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted