Incomplete In-context Learning
On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
Abstract (arXiv)
Large vision language models (LVLMs) achieve remarkable performance through Vision In-context Learning (VICL), a process that depends significantly on demonstrations retrieved from an extensive collection of annotated examples (retrieval database). Existing studies often assume that the retrieval database contains annotated examples for all labels. However, in real-world scenarios, delays in database updates or incomplete data annotation may result in the retrieval database containing labeled samples for only a subset of classes. We refer to this phenomenon as an incomplete retrieval database and define the in-context learning under this condition as Incomplete In-context Learning (IICL). To address this challenge, we propose Iterative Judgments and Integrated Prediction (IJIP), a two-stage framework designed to mitigate the limitations of IICL. The Iterative Judgments Stage reformulates an (boldsymbolm)-class classification problem into a series of (boldsymbolm) binary classification tasks, effectively converting the IICL setting into a standard VICL scenario. The Integrated Prediction Stage further refines the classification process by leveraging both the input image and the predictions from the Iterative Judgments Stage to enhance overall classification accuracy. IJIP demonstrates considerable performance across two LVLMs and two datasets under three distinct conditions of label incompleteness, achieving the highest accuracy of 93.9%. Notably, even in scenarios where labels are fully available, IJIP still achieves the best performance of all six baselines. Furthermore, IJIP can be directly applied to Prompt Learning and is adaptable to the text domain.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 36 of its 46 references that are in the map. First posted on arXiv 12 May 2025.
Builds on
36 of 46 references.
Closest ancestors · 1
Same direction, newest first
Other references · 35
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
- 2022Emergent Abilities of Large Language Modelscited by 2,512
- 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
- 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
- 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
- 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
23 more
- 2021MetaICL: Learning to Learn In Contextcited by 454
- 2023Larger language models do in-context learning differentlycited by 394
- 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 388
- 2023Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learningcited by 236
- 2022Demystifying Prompts in Language Models via Perplexity Estimationcited by 216
- 2015Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Featurecited by 182
- 2022Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Orderingcited by 161
- 2023Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learningcited by 149
- 2023Finding Support Examples for In-Context Learningcited by 104
- 2023Mitigating Label Biases for In-context Learningcited by 89
- 2023Symbol tuning improves in-context learning in language modelscited by 75
- 2022Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrationscited by 70
- 2023Meta-in-context learning in large language modelscited by 59
- 2023Coverage-based Example Selection for In-Context Learningcited by 59
- 2023In-Context Learning Learns Label Relationships but Is Not Conventional Learningcited by 51
- 2022Towards Robust Ranker for Text Retrievalcited by 37
- 2023Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selectioncited by 37
- 2023In-Context Learning for Text Classification with Many Labelscited by 35
- 2023Few-shot Class-incremental Learning for Classification and Object Detection: A Surveycited by 25
- 2023Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learningcited by 18
- 2016CIFAR-10: KNN-based Ensemble of Classifierscited by 16
- 2023How Robust are LLMs to In-Context Majority Label Bias?cited by 14
- 2024Exploring the Robustness of In-Context Learning with Noisy Labelscited by 14
Built on by
Citing papers per year: 2025: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2026Parallel In-context Learning for Large Vision Language Models
- 2023Manipulating the Label Space for In-Context Classification
- 2024Towards Multimodal In-Context Learning for Vision & Language Models
- 2025What do vision-language models see in the context? Investigating multimodal in-context learning
- 2026In-Context Collapse in Vision-Language Models and How to Mitigate it?
- 2023How to Configure Good In-Context Sequence for Visual Question Answering
- 2023MetaVL: Transferring In-Context Learning Ability From Language Models to Vision-Language Models
- 2023Towards More Unified In-context Visual Understanding