Keep the General, Inject the Specific: Structured Dialogue Fine-Tuning for Knowledge Injection without Catastrophic Forgetting

• URL: http://arxiv.org/abs/2505.00029v1
• Date: Sun, 27 Apr 2025 18:04:02 GMT
• Title: Keep the General, Inject the Specific: Structured Dialogue Fine-Tuning for Knowledge Injection without Catastrophic Forgetting
• Authors: Yijie Hong, Xiaofei Yin, Xinzhong Wang, Yi Tu, Ya Guo, Sufeng Duan, Weiqiang Wang, Lingyong Fang, Depeng Wang, Huijia Zhu,
• Abstract summary: Large Vision Language Models have demonstrated impressive versatile capabilities through extensive multimodal pre-training.<n>These models struggle with a fundamental dilemma: direct adaptation approaches that inject domain-specific knowledge often trigger catastrophic forgetting of foundational visual-linguistic abilities.<n>We introduce Structured Dialogue Fine-Tuning (SDFT), an effective approach that effectively injects domain-specific knowledge while minimizing catastrophic forgetting.
• Score: 24.67373225584835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Vision Language Models have demonstrated impressive versatile capabilities through extensive multimodal pre-training, but face significant limitations when incorporating specialized knowledge domains beyond their training distribution. These models struggle with a fundamental dilemma: direct adaptation approaches that inject domain-specific knowledge often trigger catastrophic forgetting of foundational visual-linguistic abilities. We introduce Structured Dialogue Fine-Tuning (SDFT), an effective approach that effectively injects domain-specific knowledge while minimizing catastrophic forgetting. Drawing inspiration from supervised fine-tuning in LLMs and subject-driven personalization in text-to-image diffusion models, our method employs a three-phase dialogue structure: Foundation Preservation reinforces pre-trained visual-linguistic alignment through caption tasks; Contrastive Disambiguation introduces carefully designed counterfactual examples to maintain semantic boundaries; and Knowledge Specialization embeds specialized information through chain-of-thought reasoning. Experimental results across multiple domains confirm SDFT's effectiveness in balancing specialized knowledge acquisition with general capability retention. Our key contributions include a data-centric dialogue template that balances foundational alignment with targeted knowledge integration, a weighted multi-turn supervision framework, and comprehensive evaluation across diverse knowledge types.

Related papers

• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• Structure-aware Domain Knowledge Injection for Large Language Models [38.08691252042949]
  StructTuning is a methodology to transform Large Language Models (LLMs) into domain specialists.<n>It significantly reduces the training corpus needs to a mere 5% while achieving an impressive 100% of traditional knowledge injection performance.
  arXiv  Detail & Related papers  (2024-07-23T12:38:48Z)
• Large Language Models are Limited in Out-of-Context Knowledge Reasoning [65.72847298578071]
  Large Language Models (LLMs) possess extensive knowledge and strong capabilities in performing in-context reasoning. This paper focuses on a significant aspect of out-of-context reasoning: Out-of-Context Knowledge Reasoning (OCKR), which is to combine multiple knowledge to infer new knowledge.
  arXiv  Detail & Related papers  (2024-06-11T15:58:59Z)
• Diffusion Features to Bridge Domain Gap for Semantic Segmentation [2.8616666231199424]
  This paper investigates the approach that leverages the sampling and fusion techniques to harness the features of diffusion models efficiently. By leveraging the strength of text-to-image generation capability, we introduce a new training framework designed to implicitly learn posterior knowledge from it.
  arXiv  Detail & Related papers  (2024-06-02T15:33:46Z)
• Domain Prompt Learning with Quaternion Networks [49.45309818782329]
  We propose to leverage domain-specific knowledge from domain-specific foundation models to transfer the robust recognition ability of Vision-Language Models to specialized domains. We present a hierarchical approach that generates vision prompt features by analyzing intermodal relationships between hierarchical language prompt features and domain-specific vision features. Our proposed method achieves new state-of-the-art results in prompt learning.
  arXiv  Detail & Related papers  (2023-12-12T08:49:39Z)
• Knowledge Plugins: Enhancing Large Language Models for Domain-Specific Recommendations [50.81844184210381]
  We propose a general paradigm that augments large language models with DOmain-specific KnowledgE to enhance their performance on practical applications, namely DOKE. This paradigm relies on a domain knowledge extractor, working in three steps: 1) preparing effective knowledge for the task; 2) selecting the knowledge for each specific sample; and 3) expressing the knowledge in an LLM-understandable way.
  arXiv  Detail & Related papers  (2023-11-16T07:09:38Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)
• A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision [17.875098424936542]
  We present FLAIR, a pre-trained vision-language model for universal retinal fundus image understanding.<n>We compiled 38 open-access, mostly categorical fundus imaging datasets from various sources.<n>We integrate the expert's domain knowledge in the form of descriptive textual prompts, during both pre-training and zero-shot inference.
  arXiv  Detail & Related papers  (2023-08-15T17:39:52Z)
• Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation [68.13453771001522]
  We propose a multimodal intensive ZSL framework that matches regions of images with corresponding semantic embeddings. We conduct extensive experiments and evaluate our model on large-scale real-world data.
  arXiv  Detail & Related papers  (2023-06-14T13:07:48Z)
• CLIP-Driven Fine-grained Text-Image Person Re-identification [50.94827165464813]
  TIReID aims to retrieve the image corresponding to the given text query from a pool of candidate images. We propose a CLIP-driven Fine-grained information excavation framework (CFine) to fully utilize the powerful knowledge of CLIP for TIReID.
  arXiv  Detail & Related papers  (2022-10-19T03:43:12Z)
• Contrastive Language-Image Pre-Training with Knowledge Graphs [33.211811772961234]
  We propose a knowledge-based pre-training framework, dubbed Knowledge-CLIP, which injects semantic information into the widely used CLIP model. Our model can semantically align the representations in vision and language with higher quality, and enhance the reasoning ability across scenarios and modalities.
  arXiv  Detail & Related papers  (2022-10-17T09:49:22Z)
• Knowledge-grounded Dialog State Tracking [12.585986197627477]
  We propose to perform dialog state tracking grounded on knowledge encoded externally. We query relevant knowledge of various forms based on the dialog context. We demonstrate superior performance of our proposed method over strong baselines.
  arXiv  Detail & Related papers  (2022-10-13T01:34:08Z)

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.