Calibrated Self-Rewarding Vision Language Models
- URL: http://arxiv.org/abs/2405.14622v3
- Date: Fri, 31 May 2024 16:37:53 GMT
- Title: Calibrated Self-Rewarding Vision Language Models
- Authors: Yiyang Zhou, Zhiyuan Fan, Dongjie Cheng, Sihan Yang, Zhaorun Chen, Chenhang Cui, Xiyao Wang, Yun Li, Linjun Zhang, Huaxiu Yao,
- Abstract summary: 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.
- Score: 27.686545023186852
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. Despite these advancements, LVLMs often exhibit the hallucination phenomenon, where generated text responses appear linguistically plausible but contradict the input image, indicating a misalignment between image and text pairs. This misalignment arises because the model tends to prioritize textual information over visual input, even when both the language model and visual representations are of high quality. Existing methods leverage additional models or human annotations to curate preference data and enhance modality alignment through preference optimization. These approaches may not effectively reflect the target LVLM's preferences, making the curated preferences easily distinguishable. Our work addresses these challenges by proposing 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. In the reward modeling, we employ a step-wise strategy and incorporate visual constraints into the self-rewarding process to place greater emphasis on visual input. Empirical results demonstrate that CSR enhances performance and reduces hallucinations across ten benchmarks and tasks, achieving substantial improvements over existing methods by 7.62%. Our empirical results are further supported by rigorous theoretical analysis, under mild assumptions, verifying the effectiveness of introducing visual constraints into the self-rewarding paradigm. Additionally, CSR shows compatibility with different vision-language models and the ability to incrementally improve performance through iterative fine-tuning. Our data and code are available at https://github.com/YiyangZhou/CSR.
Related papers
- Enhancing Large Vision Language Models with Self-Training on Image Comprehension [99.9389737339175]
We introduce Self-Training on Image (STIC), which emphasizes a self-training approach specifically for image comprehension.
First, the model self-constructs a preference for image descriptions using unlabeled images.
To further self-improve reasoning on the extracted visual information, we let the model reuse a small portion of existing instruction-tuning data.
arXiv Detail & Related papers (2024-05-30T05:53:49Z) - Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement [102.22911097049953]
SIMA is a framework that enhances visual and language modality alignment through self-improvement.
It employs an in-context self-critic mechanism to select response pairs for preference tuning.
We demonstrate that SIMA achieves superior modality alignment, outperforming previous approaches.
arXiv Detail & Related papers (2024-05-24T23:09:27Z) - 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) - 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) - Vision-Enhanced Semantic Entity Recognition in Document Images via
Visually-Asymmetric Consistency Learning [19.28860833813788]
Existing models commonly train a visual encoder with weak cross-modal supervision signals.
We propose a novel textbfVisually-textbfAsymmetric cotextbfNsistentextbfCy textbfLearning (textscVancl) approach to capture fine-grained visual and layout features.
arXiv Detail & Related papers (2023-10-23T10:37:22Z) - Expedited Training of Visual Conditioned Language Generation via
Redundancy Reduction [61.16125290912494]
$textEVL_textGen$ is a framework designed for the pre-training of visually conditioned language generation models.
We show that our approach accelerates the training of vision-language models by a factor of 5 without a noticeable impact on overall performance.
arXiv Detail & Related papers (2023-10-05T03:40:06Z) - ILLUME: Rationalizing Vision-Language Models through Human Interactions [18.701950647429]
We propose a tuning paradigm based on human interactions with machine-generated data.
Our ILLUME executes the following loop: Given an image-question-answer prompt, the VLM samples multiple candidate rationales, and a human critic provides feedback via preference selection.
This loop increases the training data and gradually carves out the VLM's rationalization capabilities that are aligned with human intent.
arXiv Detail & Related papers (2022-08-17T11:41:43Z) - 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.